> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Monday MCP

> Manage monday.com boards, items, and workspaces through its MCP server.

![Monday MCP logo](https://mintcdn.com/composio-preview/9YPuzjEU4UlMnwGq/images/toolkits/monday_mcp.svg?fit=max\&auto=format\&n=9YPuzjEU4UlMnwGq\&q=85\&s=a8ffb4a73714183b8ca4fd78048ba528)

* **Category:** project management
* **Auth:** DCR\_OAUTH
* **Composio-managed OAuth available?** No
* **Tools:** 96
* **Triggers:** 0
* **Slug:** `MONDAY_MCP`
* **Version:** 20261030\_00

## Tools

> [accordion] Agent catalog
>
> **Slug:** `MONDAY_MCP_AGENT_CATALOG`
>
> Browse the account-wide catalog of available trigger types and skills for monday platform agents. READ-ONLY — no agent\_id required.
>
> Use this tool to discover what's available BEFORE wiring anything to a specific agent.
>
> ACTIONS:
>
> * list\_triggers: \{ block\_reference\_ids? } — returns available trigger types. Each entry has block\_reference\_id (required for manage\_agent\_triggers action:"add"), name, description, field\_schemas (describes field\_values shape), and required\_fields (fields to collect from the user). Note: only triggers that can be added programmatically appear here. OAuth/3rd-party triggers (Slack, Gmail, Salesforce, etc.) require user setup in the monday.com UI and will not appear here.
> * list\_skills: \{} — returns available skills with id, name, description. Never guess or invent a skill id — always look it up here before calling manage\_agent\_skills action:"add".
>
> USAGE EXAMPLES:
>
> * List all trigger types:    \{ "action": "list\_triggers" }
> * Fetch specific trigger:    \{ "action": "list\_triggers", "block\_reference\_ids": \["some-block-ref-id"] }
> * List all skills:           \{ "action": "list\_skills" }
>
> RELATED TOOLS:
>
> * manage\_agent\_jobs — use block\_reference\_id from list\_triggers to configure jobs with nested triggers
> * manage\_agent\_triggers — use block\_reference\_id from list\_triggers to attach a trigger to a specific agent
> * manage\_agent\_skills — use skill id from list\_skills, or action:"create" to author a new skill, then attach to an agent
> * manage\_agent — manage the agent entity itself (create, update, delete, activate, etc.)
>
> #### Input Parameters
>
> **action** `string ("list_triggers" | "list_skills")` *required*
>
> "list\_triggers" — fetch available trigger types with block\_reference\_id, field\_schemas, and required\_fields. Call before adding triggers with manage\_agent\_jobs or manage\_agent\_triggers. "list\_skills" — fetch available skills with id, name, description. Call before using manage\_agent\_skills action:"add".
>
> **block\_reference\_ids** `array`
>
> Used with action:"list\_triggers". Fetch specific trigger types by block\_reference\_id. Omit to return all trigger types.

> [accordion] All api read
>
> **Slug:** `MONDAY_MCP_ALL_API_READ`
>
> Execute read-only GraphQL queries against the monday.com API. Only queries are accepted — mutations are rejected with an error before the request is sent. Use the get\_type\_details tool first to understand the schema before crafting your query.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Custom GraphQL query/mutation. you need to provide the full query / mutation
>
> **variables** `string` *required*
>
> JSON string containing the variables for the GraphQL operation

> [accordion] All api write
>
> **Slug:** `MONDAY_MCP_ALL_API_WRITE`
>
> Execute GraphQL mutations against the monday.com API to create, update, or delete data. Only mutations are accepted — queries are rejected with an error before the request is sent. Use get\_graphql\_schema and get\_type\_details tools first to understand the schema before crafting your mutation.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Custom GraphQL query/mutation. you need to provide the full query / mutation
>
> **variables** `string` *required*
>
> JSON string containing the variables for the GraphQL operation

> [accordion] All monday api
>
> **Slug:** `MONDAY_MCP_ALL_MONDAY_API`
>
> Execute any monday.com API operation by generating GraphQL queries and mutations dynamically. Make sure you ask only for the fields you need and nothing more. When providing the query/mutation - use get\_graphql\_schema and get\_type\_details tools first to understand the schema before crafting your query.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Custom GraphQL query/mutation. you need to provide the full query / mutation
>
> **variables** `string` *required*
>
> JSON string containing the variables for the GraphQL operation

> [accordion] All widgets schema
>
> **Slug:** `MONDAY_MCP_ALL_WIDGETS_SCHEMA`
>
> Fetch complete JSON Schema 7 definitions for all available widget types in monday.com.
>
> This tool is essential before creating widgets as it provides:
>
> * Complete schema definitions for all supported widgets
> * Required and optional fields for each widget type
> * Data type specifications and validation rules
> * Detailed descriptions of widget capabilities
>
> Use this tool when you need to:
>
> * Understand widget configuration requirements before creating widgets
> * Validate widget settings against official schemas
> * Plan widget implementations with proper data structures
>
> The response includes JSON Schema 7 definitions that describe exactly what settings each widget type accepts.

> [accordion] Board insights
>
> **Slug:** `MONDAY_MCP_BOARD_INSIGHTS`
>
> This tool allows you to calculate insights about board's data by filtering, grouping and aggregating columns. For example, you can get the total number of items in a board, the number of items in each status, the number of items in each column, etc. Use this tool when you need to get a summary of the board's data, for example, you want to know the total number of items in a board, the number of items in each status, the number of items in each column, etc.\[REQUIRED PRECONDITION]: Before using this tool, if new columns were added to the board or if you are not familiar with the board's structure (column IDs, column types, status labels, etc.), first use get\_board\_info with filters.columns.only to get column metadata without fetching views. This is essential for constructing proper filters and knowing which columns are available.\[IMPORTANT]: For some columns, human-friendly label is returned inside 'LABEL\_\<column\_id' field. E.g. for column with id 'status\_123' the label is returned inside 'LABEL\_status\_123' field.
>
> #### Input Parameters
>
> **limit** `number`
>
> The limit of the results
>
> **boardId** `number` *required*
>
> The id of the board to get insights for
>
> **filters** `array`
>
> The configuration of filters to apply on the items. Use get\_board\_info with filters.columns.only for column ids and types on the board. Before sending the filters, use get\_column\_type\_info with fetchMode "guidelines" and use data.guidelines.filter (null if that type has no documented rules).
>
> **groupBy** `array`
>
> The columns to group by. All columns in the group by must be in the aggregations as well without a function.
>
> **orderBy** `array`
>
> The columns to order by, will control the order of the items in the response
>
> **aggregations** `array`
>
> The aggregations to get. Before sending the aggregations, read guidelines.aggregation from get\_column\_type\_info with fetchMode "guidelines" for a relevant column type on this board. Transformative functions and plain columns (no function) must be in group by.
>
> **filtersOperator** `string ("and" | "or")`
>
> The operator to use for the filters

> [accordion] Change item column values
>
> **Slug:** `MONDAY_MCP_CHANGE_ITEM_COLUMN_VALUES`
>
> Change the column values of a single item on a monday.com board. \[IMPORTANT] If you need to update multiple items in one call, use update\_items instead of calling this tool in a loop. Otherwise: change the column values of a single item in a monday.com board. \[REQUIRED PRECONDITION]: Before using this tool, if new columns were added to the board or if you are not familiar with the board's structure (column IDs, column types, status labels, etc.), first use get\_board\_info with filters.columns.only to get column metadata without fetching views. This is essential for constructing valid column values. For board-relation linking tasks, call link\_board\_items\_workflow before using this tool.
>
> #### Input Parameters
>
> **itemId** `number` *required*
>
> The ID of the item to be updated
>
> **boardId** `number` *required*
>
> The ID of the board that contains the item to be updated
>
> **columnValues** `string` *required*
>
> A string containing the new column values for the item following this structure: \{"column\_id": "value",... you can change multiple columns at once, note that for status column you must use nested value with 'label' as a key and for date column use 'date' as key} - example: "\{"text\_column\_id":"New text", "status\_column\_id":\{"label":"Done"}, "date\_column\_id":\{"date":"2023-05-25"}, "phone\_id":"123-456-7890", "email\_id":"[test@example.com](mailto:test@example.com)"}"
>
> **createLabelsIfMissing** `boolean`
>
> If true, create missing Status/Dropdown labels when setting those columns. Requires permission to change board structure. Omit or false to only use existing labels.

> [accordion] Connect external agent
>
> **Slug:** `MONDAY_MCP_CONNECT_EXTERNAL_AGENT`
>
> Connect a custom external agent (an agent running on your own server/infra) to monday.com.
>
> \{ custom: \{ name, callback\_url? } }
>
> Returns the new agent\_id plus a one-time signing\_secret and api\_token used to verify webhook requests and call the monday.com API/MCP server — both are shown ONLY in this response, so capture them immediately.
>
> RULES:
>
> * Omitting callback\_url creates the agent without a webhook — it won't be mentionable/assignable until one is added.
> * This tool is for CUSTOM agents only. For Claude, OpenAI, and other supported providers, use manage\_agent.
>
> #### Input Parameters
>
> **custom** `object` *required*
>
> Provide this to connect a custom external agent.

> [accordion] Create action
>
> **Slug:** `MONDAY_MCP_CREATE_ACTION`
>
> Save a reusable action (a stored code script). Variables are injected as environment variables (access via os.environ in Python, process.env in JS/TS).
>
> Recommended: Test your code with execute\_code before saving to ensure it works correctly.
>
> Network access is restricted to the following hosts: \[api.monday.com/, mcp.monday.com/mcp]. Requests to any other host will be blocked.
>
> Example: name: "Get board items", description: "Fetches items from a board", language: "python", code: "import requests\nprint('done')"
>
> #### Input Parameters
>
> **code** `string` *required*
>
> Source code (max 1 MB)
>
> **name** `string` *required*
>
> Short, descriptive action name
>
> **language** `string ("javascript" | "typescript" | "python")` *required*
>
> Programming language — one of: javascript, typescript, python
>
> **description** `string` *required*
>
> Short summary: what data the code accesses (specific boards/items by name or ID, or scope if broad), what processing it performs, and how the result is returned. Max 255 characters. Write this well — it is how the action is discovered and reused later.
>
> **vars\_schema** `array`
>
> Variable definitions — injected as environment variables at execution time
>
> **output\_description** `string` *required*
>
> Required. Instructions describing what should be done with the execution output (e.g. "post the summary as an update on item 123"), max 2000 characters. Echoed back in the run\_action response.

> [accordion] Create automation
>
> **Slug:** `MONDAY_MCP_CREATE_AUTOMATION`
>
> Creates an automation on a monday board from a structured natural-language description.
>
> Use this tool only when you know:
>
> * boardId
> * the user's intended trigger
> * at least one intended action
> * any details the user provided that are relevant to the trigger, conditions, or actions
>
> The caller does not need to know the exact available automation blocks or their required fields. Describe the user's intent clearly — the tool will translate that intent into supported blocks and values.
>
> If a required detail is missing from the user's request, ask for clarification before calling the tool.
>
> If the tool returns status: "needs\_clarification", present the unresolved fields to the user, gather answers, then call the tool again.
>
> Describe the automation in this format:
>
> Trigger: When \<the event that should start the automation> Details: \<relevant detail>: \<value>
>
> Conditions:
>
> * Only if \<condition that should be true> Details: \<relevant detail>: \<value>
>
> Actions:
>
> * \<action the automation should perform>: \<relevant detail>: \<value>
>
> Rules:
>
> * Use one trigger.
> * Conditions are optional.
> * Multiple conditions mean AND.
> * Use one or more actions.
> * Do not use branching.
> * Use natural language, not block IDs or internal field names.
> * Actions may reference values from the trigger context, such as "\{\{item name}}", "\{\{creator}}", "\{\{status}}", "\{\{group}}", or "\{\{board}}".
>
> Terminology:
>
> * Trigger: the event that starts the automation, such as "when a new item is created".
> * Conditions: optional requirements that must be true before actions run.
> * Actions: what the automation does when it runs.
>
> Example:
>
> Trigger: When a new item is created
>
> Actions:
>
> * Send a notification: Recipient: John Snow Title: Important Update Message: The item "\{\{item name}}" was created.
> * Move the item to a group: Group: Top group
>
> #### Input Parameters
>
> **boardId** `string` *required*
>
> The numeric board ID as a string.
>
> **userPrompt** `string` *required*
>
> Structured description of the automation to create.

> [accordion] Create board
>
> **Slug:** `MONDAY_MCP_CREATE_BOARD`
>
> Create a monday.com board. Use creationPrompt to describe how you want the board to be built
>
> #### Input Parameters
>
> **folderId** `integer`
>
> The folder ID to create the board in
>
> **boardKind** `string ("private" | "public" | "share")` *required*
>
> The kind of board to create
>
> **boardName** `string` *required*
>
> The name of the board to create
>
> **workspaceId** `string`
>
> The workspace ID to create the board in
>
> **boardOwnerIds** `array`
>
> The IDs of the board owners
>
> **creationPrompt** `string`
>
> Describe in free text how you want the board to be built. Omit to create an empty board.
>
> **useMlsTemplate** `boolean`
>
> Set to true to create a multi-level board using the MLS template
>
> **boardDescription** `string`
>
> The description of the board
>
> **useDatasetTemplate** `boolean`
>
> Set to true to create a board from the dataset template

> [accordion] Create column
>
> **Slug:** `MONDAY_MCP_CREATE_COLUMN`
>
> Create a new column in a monday.com board. \[REQUIRED PRECONDITION]: If the column needs type-specific configuration (columnSettings) — e.g. status/dropdown labels, formula definitions, number units — first call get\_column\_type\_info with fetchMode "schema" for that column type to learn the valid settings structure. Do not guess the settings shape. To give the new column AI behavior, create it here first, then call configure\_ai\_column.
>
> #### Input Parameters
>
> **boardId** `number` *required*
>
> The id of the board to which the new column will be added
>
> **columnType** `string ("auto_number" | "board_relation" | "button" | "checkbox" | "color_picker" | "country" | "creation_log" | "date" | "dependency" | "direct_doc" | "doc" | "dropdown" | "email" | "file" | "formula" | "group" | "hour" | "integration" | "item_assignees" | "item_id" | "last_updated" | "link" | "location" | "long_text" | "mirror" | "name" | "numbers" | "people" | "phone" | "progress" | "rating" | "status" | "subtasks" | "tags" | "team" | "text" | "time_tracking" | "timeline" | "unsupported" | "vote" | "week" | "world_clock")` *required*
>
> The type of the column to be created
>
> **columnTitle** `string` *required*
>
> The title of the column to be created
>
> **columnSettings** `string`
>
> Column-specific configuration settings as a JSON string. Shape depends on columnType — see tool description for how to obtain it.
>
> **columnDescription** `string`
>
> The description of the column to be created

> [accordion] Create dashboard
>
> **Slug:** `MONDAY_MCP_CREATE_DASHBOARD`
>
> Use this tool to create a new monday.com dashboard that aggregates data from one or more boards. Dashboards provide visual representations of board data through widgets and charts.
>
> Use this tool when users want to:
>
> * Create a dashboard to visualize board data
> * Aggregate information from multiple boards
> * Set up a data visualization container for widgets
>
> #### Input Parameters
>
> **kind** `string ("PRIVATE" | "PUBLIC")`
>
> Visibility level: PUBLIC or PRIVATE
>
> **name** `string` *required*
>
> Human-readable dashboard title (UTF-8 chars)
>
> **board\_ids** `array` *required*
>
> List of board IDs as strings (min 1 element)
>
> **workspace\_id** `string` *required*
>
> ID of the workspace that will own the dashboard
>
> **board\_folder\_id** `string`
>
> Optional folder ID within workspace to place this dashboard (if not provided, dashboard will be placed in workspace root)

> [accordion] Create doc
>
> **Slug:** `MONDAY_MCP_CREATE_DOC`
>
> Create a new monday.com doc either inside a workspace or attached to an item (via a doc column). After creation, the provided markdown will be appended to the document.
>
> LOCATION TYPES:
>
> * workspace: Creates a document in a workspace (requires workspace\_id, optional doc\_kind, optional folder\_id, optional docOwnerIds)
> * item: Creates a document attached to an item (requires item\_id, optional column\_id, optional docOwnerIds)
>
> USAGE EXAMPLES:
>
> * Workspace doc: \{ location: "workspace", workspace\_id: 123, doc\_name: "My Doc", doc\_kind: "private" , markdown: "..." }
> * Workspace doc in folder: \{ location: "workspace", workspace\_id: 123, doc\_name: "My Doc", folder\_id: 17264196 , markdown: "..." }
> * Item doc: \{ location: "item", item\_id: 456, doc\_name: "My Doc", column\_id: "doc\_col\_1" , markdown: "..." }
> * Workspace doc with agent owner: \{ location: "workspace", workspace\_id: 123, doc\_name: "My Doc", markdown: "...", docOwnerIds: \["\<agent\_owner\_user\_id>"] }
>
> #### Input Parameters
>
> **item\_id** `number`
>
> \[REQUIRED - use only when location="item"] Item ID to attach the new document to
>
> **doc\_kind** `string ("private" | "public" | "share")`
>
> \[OPTIONAL - use only when location="workspace"] Document kind (public/private/share). Defaults to public.
>
> **doc\_name** `string` *required*
>
> Name for the new document.
>
> **location** `string ("workspace" | "item")` *required*
>
> Location where the document should be created - either in a workspace or attached to an item
>
> **markdown** `string` *required*
>
> Markdown content that will be imported into the newly created document as blocks.
>
> **column\_id** `string`
>
> \[OPTIONAL - use only when location="item"] ID of an existing "doc" column on the board which contains the item. If not provided, the tool will create a new doc column automatically when creating a doc on an item.
>
> **folder\_id** `number`
>
> \[OPTIONAL - use only when location="workspace"] Optional folder ID to place the document inside a specific folder
>
> **docOwnerIds** `array`
>
> Optional list of user IDs to set as document owners at creation time. Use this to add the agent owner so they retain access to the document. Ownership is set inside the creation mutation itself, bypassing the permission checks that would block a subsequent add\_subscribers\_to\_object call.
>
> **workspace\_id** `number`
>
> \[REQUIRED - use only when location="workspace"] Workspace ID under which to create the new document

> [accordion] Create folder
>
> **Slug:** `MONDAY_MCP_CREATE_FOLDER`
>
> Create a new folder in a monday.com workspace
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name of the folder to be created
>
> **color** `string ("AQUAMARINE" | "BRIGHT_BLUE" | "BRIGHT_GREEN" | "CHILI_BLUE" | "DARK_ORANGE" | "DARK_PURPLE" | "DARK_RED" | "DONE_GREEN" | "INDIGO" | "LIPSTICK" | "NULL" | "PURPLE" | "SOFIA_PINK" | "STUCK_RED" | "SUNSET" | "WORKING_ORANGE")`
>
> The color of the folder
>
> **customIcon** `string ("FOLDER" | "MOREBELOW" | "MOREBELOWFILLED" | "NULL" | "WORK")`
>
> The custom icon of the folder
>
> **fontWeight** `string ("FONT_WEIGHT_BOLD" | "FONT_WEIGHT_LIGHT" | "FONT_WEIGHT_NORMAL" | "FONT_WEIGHT_VERY_LIGHT" | "NULL")`
>
> The font weight of the folder
>
> **workspaceId** `string` *required*
>
> The ID of the workspace where the folder will be created
>
> **parentFolderId** `string`
>
> The ID of the parent folder

> [accordion] Create form
>
> **Slug:** `MONDAY_MCP_CREATE_FORM`
>
> Create a monday.com form. Also creates a backing board to store responses. Returns the formToken for future mutations.
>
> #### Input Parameters
>
> **board\_kind** `string ("private" | "public" | "share")`
>
> **board\_owner\_ids** `array`
>
> **destination\_name** `string`
>
> Board name (stores form responses).
>
> **board\_owner\_team\_ids** `array`
>
> **board\_subscriber\_ids** `array`
>
> User IDs to notify on board activity.
>
> **destination\_folder\_id** `string`
>
> **destination\_folder\_name** `string`
>
> **destination\_workspace\_id** `string` *required*
>
> **board\_subscriber\_teams\_ids** `array`
>
> Team IDs to notify on board activity.

> [accordion] Create form submission
>
> **Slug:** `MONDAY_MCP_CREATE_FORM_SUBMISSION`
>
> Submit a response to a monday.com WorkForm. Use get\_form first to retrieve the WorkForm, then:
>
> * Inspect each question's showIfRules to determine which questions are conditionally shown based on previous answers.
> * Inspect each question's settings for any answer constraints (e.g. rating limits, select options, label limits).
> * Take note of any titles, descriptions, and content blocks to present the form naturally as you walk the user through it.
> * Take note of pages and question order to present questions in the correct sequence. Gather all answers upfront before calling this tool — do not submit one question at a time. Accepts a bare form token, a full WorkForm URL (e.g. [https://forms.monday.com/forms/\&#123;form\_token\&#125;?r=use1](https://forms.monday.com/forms/\&#123;form_token\&#125;?r=use1)), or a shortened wkf.ms URL (e.g. [https://wkf.ms/4tqP28t](https://wkf.ms/4tqP28t)) — shortened URLs are automatically resolved by following the redirect. Returns the submission ID.
>
> #### Input Parameters
>
> **tags** `array`
>
> Tags to attach to the submission — each tag maps a value to a specific board column.
>
> **answers** `array` *required*
>
> Array of answers to submit. Each answer specifies a question\_id and the value for that question type.
>
> **password** `string`
>
> The password for the WorkForm. Only required if the WorkForm has password protection enabled (check features.password.enabled from get\_form). If required, ask the user for the password before submitting.
>
> **form\_token** `string` *required*
>
> The unique token identifying the WorkForm. Can be a bare token, a full WorkForm URL (e.g. [https://forms.monday.com/forms/abc123?r=use1](https://forms.monday.com/forms/abc123?r=use1)), or a shortened wkf.ms URL (e.g. [https://wkf.ms/4tqP28t](https://wkf.ms/4tqP28t)). Shortened URLs are automatically resolved by following the redirect.
>
> **form\_timezone\_offset** `integer` *required*
>
> The timezone offset of the submitter in minutes (e.g. -120 for UTC-2, 0 for UTC).

> [accordion] Create group
>
> **Slug:** `MONDAY_MCP_CREATE_GROUP`
>
> Create a new group in a monday.com board. Groups are sections that organize related items. Use when users want to add structure, categorize items, or create workflow phases. Groups can be positioned relative to existing groups and assigned predefined colors. Items will always be created in the top group and so the top group should be the most relevant one for new item creation
>
> #### Input Parameters
>
> **boardId** `string` *required*
>
> The ID of the board to create the group in
>
> **groupName** `string` *required*
>
> The name of the new group (maximum 255 characters)
>
> **groupColor** `string ("#037f4c" | "#00c875" | "#9cd326" | "#cab641" | "#ffcb00" | "#784bd1" | "#9d50dd" | "#007eb5" | "#579bfc" | "#66ccff" | "#bb3354" | "#df2f4a" | "#ff007f" | "#ff5ac4" | "#ff642e" | "#fdab3d" | "#7f5347" | "#c4c4c4" | "#757575")`
>
> The color for the group. Must be one of the predefined Monday.com group colors: #037f4c, #00c875, #9cd326, #cab641, #ffcb00, #784bd1, #9d50dd, #007eb5, #579bfc, #66ccff, #bb3354, #df2f4a, #ff007f, #ff5ac4, #ff642e, #fdab3d, #7f5347, #c4c4c4, #757575
>
> **relativeTo** `string`
>
> The ID of the group to position this new group relative to
>
> **positionRelativeMethod** `string ("after_at" | "before_at")`
>
> Whether to position the new group before or after the relativeTo group

> [accordion] Create item
>
> **Slug:** `MONDAY_MCP_CREATE_ITEM`
>
> Create a single item or subitem on a monday.com board, or duplicate an existing item. \[IMPORTANT] If you need to create multiple items in one call, use create\_items instead of calling this tool in a loop. Otherwise: create a new item with provided values, create a subitem under a parent item, or duplicate an existing item and update it with new values. Use parentItemId when creating a subitem under an existing item. Use duplicateFromItemId when copying an existing item with modifications. \[REQUIRED PRECONDITION]: Before using this tool, if new columns were added to the board or if you are not familiar with the board's structure (column IDs, column types, status labels, etc.), first use get\_board\_info with filters.columns.only to get column metadata without fetching views. This is essential for constructing proper column values and knowing which columns are available.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name of the new item to be created, must be relevant to the user's request. 1–255 characters.
>
> **boardId** `number` *required*
>
> The id of the board to which the new item will be added
>
> **groupId** `string`
>
> The id of the group id to which the new item will be added, if its not clearly specified, leave empty
>
> **columnValues** `string` *required*
>
> A JSON string of column values, keyed by column id. Status and dropdown columns must use \{ "label": "..." } (or \{ "labels": \["...", "..."] } for multi-select dropdown). Date columns use \{ "date": "YYYY-MM-DD" }. Text/number/email/phone use plain strings. Example: "\{"text\_col":"hello", "status\_col":\{"label":"Done"}, "date\_col":\{"date":"2023-05-25"}, "dropdown\_col":\{"labels":\["A","B"]}, "phone\_col":"123-456-7890", "email\_col":"[test@example.com](mailto:test@example.com)"}". If you don't know the exact label values or column ids, call get\_board\_info first.
>
> **parentItemId** `number`
>
> The id of the parent item under which the new subitem will be created
>
> **duplicateFromItemId** `number`
>
> The id of existing item to duplicate and update with new values (only provide when duplicating)
>
> **createLabelsIfMissing** `boolean`
>
> When true, missing status/dropdown labels referenced in columnValues will be auto-created on the board instead of erroring with ColumnValueException. Requires permission to change board structure. Use when the caller specifies label names that may not yet exist on the board.

> [accordion] Create items
>
> **Slug:** `MONDAY_MCP_CREATE_ITEMS`
>
> Create up to 20 new items in a single call. Each item is fully independent - it chooses its own groupId, parentItemId (for subitems), duplicateFromItemId (for bulk templating from an existing item), and createLabelsIfMissing. A single call can therefore span multiple groups, mix regular items with subitems under different parents, and mix fresh creates with duplicates of existing items. Each item returns its own item\_id and item\_url on success, or a raw error message on failure. \[REQUIRED PRECONDITION]: Before using this tool, if new columns were added to the board or if you are not familiar with the board's structure (column IDs, column types, status labels, etc.), first use get\_board\_info with filters.columns.only to get column metadata without fetching views. This is essential for constructing proper column values and knowing which columns are available.
>
> #### Input Parameters
>
> **items** `array` *required*
>
> The items to create, up to 20 per call. Each item returns its own item\_id and item\_url on success, or a raw error message on failure. Each item independently chooses its groupId, parentItemId, and createLabelsIfMissing.
>
> **boardId** `number` *required*
>
> The id of the board to which the new items will be added

> [accordion] Create notification
>
> **Slug:** `MONDAY_MCP_CREATE_NOTIFICATION`
>
> Send a notification to a user via the bell icon and optionally by email. Use target\_type "Post" for updates/replies or "Project" for items/boards.
>
> #### Input Parameters
>
> **text** `string` *required*
>
> The notification text
>
> **user\_id** `string` *required*
>
> The user ID to send the notification to
>
> **target\_id** `string` *required*
>
> The target ID (update/reply ID for Post type, item/board ID for Project type)
>
> **target\_type** `string ("Post" | "Project")` *required*
>
> The target type (Post for update/reply, Project for item/board)

> [accordion] Create update
>
> **Slug:** `MONDAY_MCP_CREATE_UPDATE`
>
> Create a new update (comment/post) on a monday.com item. Updates can be used to add comments, notes, or discussions to items. You can optionally mention users, teams, or boards in the update. You can also reply to an existing update by using the parentId parameter.
>
> #### Input Parameters
>
> **body** `string` *required*
>
> The update text to be created. Do not use @ to mention users, use the mentionsList field instead. use html tags to format the text, dont use markdown.
>
> **itemId** `number` *required*
>
> The id of the item to which the update will be added
>
> **parentId** `number`
>
> The ID of the update to reply to. Use this parameter when you want to reply on an existing update leave it empty if you want to create a new update
>
> **mentionsList** `string`
>
> Optional JSON array of mentions in the format: \[\{"id": "123", "type": "User"}, \{"id": "456", "type": "Team"}]. Valid types are: User, Team, Board, Project

> [accordion] Create view
>
> **Slug:** `MONDAY_MCP_CREATE_VIEW`
>
> Create a new board view (tab) with optional filters and sorting.
>
> Filter operators: any\_of, not\_any\_of, is\_empty, is\_not\_empty, greater\_than, lower\_than, between, contains\_text, not\_contains\_text View types: TABLE (standard board), DASHBOARD, FORM, APP
>
> #### Input Parameters
>
> **name** `string`
>
> The name of the view
>
> **sort** `array`
>
> Sort configuration for the view
>
> **tags** `array`
>
> Tag names used to categorize and filter views in the board header
>
> **type** `string ("TABLE" | "DASHBOARD" | "FORM" | "APP")` *required*
>
> The type of board view to create
>
> **filter** `object`
>
> Filter configuration for the view
>
> **boardId** `string` *required*
>
> The board ID to create the view on
>
> **settings** `string`
>
> Type-specific view settings as a JSON object

> [accordion] Create view table
>
> **Slug:** `MONDAY_MCP_CREATE_VIEW_TABLE`
>
> Create a new table-type board view with optional filters, sort, tags, and table-specific settings including conditional coloring (highlight rows/cells based on column values).
>
> CONDITIONAL COLORING: Use settings.conditional\_coloring to highlight rows or cells. Each rule specifies a column\_id, operator, value (human-readable — e.g. "Stuck", not an index), color, and entire\_row flag. Example: highlight rows where Status is "Stuck" in red, or where Salary > 100000 in green.
>
> Use this tool instead of create\_view when you need table-specific settings like column visibility, group-by, or conditional coloring.
>
> Filter operators: any\_of, not\_any\_of, is\_empty, is\_not\_empty, greater\_than, lower\_than, between, contains\_text, not\_contains\_text
>
> #### Input Parameters
>
> **name** `string`
>
> The name of the view
>
> **sort** `array`
>
> Sort configuration for the view
>
> **tags** `array`
>
> Tag names used to categorize and filter views in the board header
>
> **filter** `object`
>
> Filter configuration for the view
>
> **boardId** `string` *required*
>
> The board ID to create the table view on
>
> **settings** `object`
>
> Table-specific settings (column visibility/order, group-by)

> [accordion] Create widget
>
> **Slug:** `MONDAY_MCP_CREATE_WIDGET`
>
> Create a new widget in a dashboard or board view with specific configuration settings.
>
> This tool creates data visualization widgets that display information from monday.com boards: **Parent Containers:**
>
> * **DASHBOARD**: Place widget in a dashboard (most common use case)
> * **BOARD\_VIEW**: Place widget in a specific board view
>
> **Critical Requirements:**
>
> 1. **Schema Compliance**: Widget settings MUST conform to the JSON schema for the specific widget type
> 2. **Use all\_widgets\_schema first**: Always fetch widget schemas before creating widgets
> 3. **Validate settings**: Ensure all required fields are provided and data types match
>
> **Workflow:**
>
> 1. Use 'all\_widgets\_schema' to get schema definitions
> 2. Prepare widget settings according to the schema
> 3. Use this tool to create the widget
>
> #### Input Parameters
>
> **settings** `object`
>
> Widget-specific settings as JSON object conforming to widget schema. Use all\_widgets\_schema tool to get the required schema for each widget type.
>
> **widget\_kind** `string ("APP_FEATURE" | "BATTERY" | "CALENDAR" | "CHART" | "GANTT" | "LISTVIEW" | "NUMBER")` *required*
>
> Type of widget to create: i.e CHART, NUMBER, BATTERY
>
> **widget\_name** `string` *required*
>
> Widget display name (1-255 UTF-8 chars)
>
> **parent\_container\_id** `string` *required*
>
> ID of the parent container (dashboard ID or board view ID)
>
> **parent\_container\_type** `string ("BOARD_VIEW" | "DASHBOARD")` *required*
>
> Type of parent container: DASHBOARD or BOARD\_VIEW

> [accordion] Create workflow
>
> **Slug:** `MONDAY_MCP_CREATE_WORKFLOW`
>
> Creates a new empty workflow in the given workspace and returns its identifiers (workflowObjectId and workflowDraftId).
>
> Use this tool when the user wants to start a brand-new workflow from scratch, rather than modifying an existing one. Only the workspace is required; title, privacy kind, description, folder, and owners are optional and fall back to sensible defaults.
>
> The tool returns a JSON object with the identifiers of the newly created workflow, which can then be used with the other workflow tools.
>
> To build a URL to the workflow, use the template: https\://\<account\_slug>.monday.com/custom\_objects/\<workflowObjectId>. To get a real URL example of the account, call the monday GraphQL MCP tool with the query `{ me { url } }`.
>
> #### Input Parameters
>
> **title** `string`
>
> Workflow title (defaults to "New Workflow")
>
> **folderId** `string`
>
> Optional folder ID to place the workflow in
>
> **ownerIds** `array`
>
> Optional list of user IDs to set as workflow owners
>
> **description** `string`
>
> Optional workflow description
>
> **privacyKind** `string ("PUBLIC" | "PRIVATE" | "SHARE")`
>
> Privacy kind for the workflow (defaults to PUBLIC)
>
> **workspaceId** `string` *required*
>
> Workspace ID to create the workflow in

> [accordion] Create workspace
>
> **Slug:** `MONDAY_MCP_CREATE_WORKSPACE`
>
> Create a new workspace in monday.com
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name of the new workspace to be created
>
> **description** `string`
>
> The description of the new workspace
>
> **workspaceKind** `string ("closed" | "open" | "template")` *required*
>
> The kind of workspace to create
>
> **accountProductId** `string`
>
> The account product ID associated with the workspace

> [accordion] Delete action
>
> **Slug:** `MONDAY_MCP_DELETE_ACTION`
>
> Delete a saved action.
>
> Example: id: "550e8400-e29b-41d4-a716-446655440000"
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Action ID

> [accordion] Delete view
>
> **Slug:** `MONDAY_MCP_DELETE_VIEW`
>
> Delete a board view (tab) from a monday.com board. Use get\_board\_info to find the view ID before deleting.
>
> #### Input Parameters
>
> **viewId** `string` *required*
>
> The ID of the view to delete
>
> **boardId** `string` *required*
>
> The ID of the board the view belongs to

> [accordion] Execute code
>
> **Slug:** `MONDAY_MCP_EXECUTE_CODE`
>
> Run arbitrary code in a monday-authenticated sandbox, without saving.
>
> Prefer dedicated monday tools for individual reads, writes, and GraphQL queries/mutations — they render in the UI and are retried one step at a time. Reach for execute\_code when code is genuinely the better tool:
>
> * Bulk / multi-item work — batch operations, dedup, aggregations, joins across boards (one script beats N tool calls that accumulate context and compound failure)
> * Data transformation — normalizing phones/dates, fuzzy matching, weighted scoring
> * File I/O — parsing uploaded CSV/XLSX to import items, producing downloadable exports
> * Multi-step workflows where each step's output gates the next
>
> The sandbox has authenticated access to the monday.com API. You can make HTTP requests with GraphQL queries and mutations — authentication is handled automatically.
>
> IMPORTANT: Network access is restricted to the following hosts: \[api.monday.com/, mcp.monday.com/mcp]. Requests to any other host (or a different path on a restricted host) will be blocked. Use this tool to query boards, items, columns, users, updates, and any other monday.com API resource.
>
> THE SANDBOX IS PER-CALL: a new empty container every call, destroyed when the call returns. Nothing written to disk survives, /tmp included. Never write a file in one call to read it in a later one, and don't invent staging paths for earlier tool results — none exist. To carry data forward, print it and pass it into the next call's code, or do the whole job in one call. Splitting a fan-out across calls only works if the later calls don't depend on the earlier ones' files.
>
> FAIL WITH A NON-ZERO EXIT. A run that prints an error and exits 0 is recorded as a success. The monday.com API returns HTTP 200 with an "errors" array, so check the parsed body rather than the status code and raise when it is present. Let exceptions propagate; don't wrap the script in a bare try/except.
>
> TIME LIMIT: 300s. A run that exceeds it is killed, so scope each call to finish well inside the limit instead of fetching everything in one script.
>
> Don't call mcp.monday.com from inside the sandbox to reach monday tools — you already have them, and a tool missing from your tool list won't be found there either.
>
> Example — monday.com GraphQL query, raising on errors (Python). Use this shape for every API call: code: "import requests\ndef gql(query):\n    body = requests.post('[https://api.monday.com/v2](https://api.monday.com/v2)', json=\{'query': query}).json()\n    if 'errors' in body:\n        raise RuntimeError(body\['errors'])\n    return body\['data']\nprint(gql('\{ users(limit:5) \{ id name email } }'))"
>
> Example — monday.com GraphQL mutation (Python): code: "import requests\nmutation = 'mutation \{ create\_board(board\_name: "New Board", board\_kind: public) \{ id } }'\nbody = requests.post('[https://api.monday.com/v2](https://api.monday.com/v2)', json=\{'query': mutation}).json()\nif 'errors' in body:\n    raise RuntimeError(body\['errors'])\nprint(body\['data'])"
>
> Example — with vars (accessed via os.environ): code: "import os, requests\nuser\_id = os.environ\['user\_id']\nresp = requests.post('[https://api.monday.com/v2](https://api.monday.com/v2)', json=\{'query': f'\{\{ users(ids: \[\{user\_id}]) \{\{ id name email }} }}'})\nprint(resp.json())" vars: \{"user\_id": 12345}
>
> Example — simple (Python): code: "print('hello world')"
>
> Example — with files (input and output): code: "import json\ndata = json.load(open('/tmp/data.json'))\njson.dump(\{'count': len(data)}, open('/tmp/result.json', 'w'))" files: \[\{"path": "/tmp/data.json", "content": "W3siaWQiOiAxfV0="}] output\_files: \["/tmp/result.json"]
>
> Example — auto-collect outputs (write anything you want returned under /outputs): code: "import os, json\nos.makedirs('/outputs', exist\_ok=True)\njson.dump(\{'ok': True}, open('/outputs/result.json', 'w'))" return\_outputs: true
>
> #### Input Parameters
>
> **code** `string` *required*
>
> Source code to execute. Max 1 MB. Access vars via os.environ (Python), process.env (JS/TS) or "\$VAR" (bash).
>
> **vars** `object`
>
> Variables injected as environment variables into the sandbox (access via os.environ / process.env)
>
> **files** `array`
>
> Input files to write into the sandbox before execution (max 32 files). Each must have content (base64, small files only) or url (S3 presigned URL). Inline content is capped at 512 KB per file and 1 MB across all files, so pass anything larger by url rather than inline content — urls are fetched by the sandbox directly and don't count toward those limits.
>
> **language** `string ("javascript" | "typescript" | "python" | "bash")` *required*
>
> Programming language — one of: javascript, typescript, python, bash
>
> **description** `string` *required*
>
> Required. Short summary of what this code does: the data it accesses (specific boards/items by name or ID, or scope if broad), the processing it performs, and how the result is returned.
>
> **output\_files** `array`
>
> Absolute file paths to retrieve from the sandbox after execution. Returned as presigned S3 download URLs.
>
> **return\_outputs** `boolean`
>
> When true, auto-collect every file the code writes under /outputs (instead of naming each path in output\_files) and return them as presigned download URLs. Up to 20 files, 25 MB each, 100 MB total; outputs\_truncated is set in the response if a limit is hit.

> [accordion] Explore meetings
>
> **Slug:** `MONDAY_MCP_EXPLORE_MEETINGS`
>
> Discover meetings by topic, or list/browse meetings by date and access. Returns meetings ranked by keyword relevance (matched against title and AI gist — not semantic). USE THIS FIRST for topic/theme questions ("what did we decide about pricing", "find meetings about the acme deal") AND for listing/browsing ("list my recent meetings", "meetings from last week", "my last 10 meetings"). When query is omitted, returns recent meetings filtered by date/access only — this is the tool for listing. Pass returned ids to get\_meetings\_content for full content, or to search\_meetings\_content for matching passages. Only indexed meetings are candidates.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of meetings to return (1-20). Keep small - the top-ranked few are usually enough.
>
> **query** `string`
>
> What to look for, matched against each meeting's title and AI gist and ranked by relevance. Omit or leave empty to browse by date/access filters only. Pass the core subject or entity, roughly 1-4 words (e.g. "pricing roadmap" or "acme renewal"), not the full question. Drop instruction words, filler, and synonyms, which dilute the ranking.
>
> **access** `string ("OWN" | "SHARED_WITH_ME" | "SHARED_WITH_ACCOUNT" | "ALL")`
>
> Filter by access level. OWN: meetings the user participated in or invited the bot to. SHARED\_WITH\_ME: shared with the user or their team. SHARED\_WITH\_ACCOUNT: shared with the entire account. ALL: all accessible meetings. Default: OWN.
>
> **start\_time\_to** `string`
>
> Only include meetings that started at or before this UTC ISO 8601 timestamp (e.g. 2026-07-28T23:59:59Z).
>
> **start\_time\_from** `string`
>
> Only include meetings that started at or after this UTC ISO 8601 timestamp (e.g. 2026-07-28T00:00:00Z).

> [accordion] Finalize asset upload
>
> **Slug:** `MONDAY_MCP_FINALIZE_ASSET_UPLOAD`
>
> Finalize a file upload and create the asset on monday.com. Call this after uploading the file to the presigned URL from get\_asset\_upload\_url. Requires the etag value from the PUT response headers. Automatically attaches the uploaded asset to the specified file column on the item. Returns the created asset\_id.
>
> #### Input Parameters
>
> **etag** `string` *required*
>
> The ETag header value from the PUT response when uploading to the presigned URL
>
> **itemId** `string` *required*
>
> The item's unique identifier
>
> **boardId** `string` *required*
>
> The board's unique identifier
>
> **columnId** `string` *required*
>
> The file or doc column's unique identifier to attach the uploaded asset to
>
> **uploadId** `string` *required*
>
> The upload\_id returned by get\_asset\_upload\_url

> [accordion] Form questions editor
>
> **Slug:** `MONDAY_MCP_FORM_QUESTIONS_EDITOR`
>
> Create, update, or delete a question in a monday.com form. \[REQUIRED PRECONDITION]: For update and delete, call get\_form first to resolve the exact question id and see its current type and settings — never guess a question id. For create, get\_form shows the existing questions so you do not duplicate one.
>
> #### Input Parameters
>
> **action** `string ("delete" | "update" | "create")` *required*
>
> Action to perform on the question of a form. create requires question. update requires questionId and question with type always included. delete requires questionId.
>
> **question** `object`
>
> The question to create or update. Always include type, then only the fields you want to set or change.
>
> **formToken** `string` *required*
>
> **questionId** `string`
>
> Question ID. Required for update/delete.

> [accordion] Get action
>
> **Slug:** `MONDAY_MCP_GET_ACTION`
>
> Retrieve a saved action by ID.
>
> Example: id: "550e8400-e29b-41d4-a716-446655440000"
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Action ID

> [accordion] Get assets
>
> **Slug:** `MONDAY_MCP_GET_ASSETS`
>
> Get assets (files) by their IDs. Returns file metadata including name, extension, size, public URL (valid for 1 hour), thumbnail URL, upload date, and who uploaded it.
>
> #### Input Parameters
>
> **ids** `array` *required*
>
> Array of asset IDs to fetch

> [accordion] Get asset upload url
>
> **Slug:** `MONDAY_MCP_GET_ASSET_UPLOAD_URL`
>
> Get a presigned URL to upload a file to monday.com. Returns an upload\_id and upload\_url.
>
> Only call this tool if you can execute a direct HTTP PUT with binary file data and read response headers (e.g. via shell/curl). If you can't, tell the user direct file upload isn't supported here — don't call this tool.
>
> After calling this tool, upload the file to the returned URL using an HTTP PUT request and capture the ETag header from the response:
>
> curl -i -X PUT "\<upload\_url>" \
> -H "Content-Type: \<the contentType you provided>" \
> \--data-binary @\<local\_file\_path>
>
> The response includes an ETag header (e.g. ETag: "abc123...") — save this value.
>
> Then call finalize\_asset\_upload with the upload\_id, etag, board\_id, item\_id, and column\_id to complete the upload and attach the file to an item's file column.
>
> Max file size: 500MB.
>
> #### Input Parameters
>
> **fileName** `string` *required*
>
> The name of the file to upload, including extension (e.g. "report.pdf")
>
> **fileSize** `integer` *required*
>
> The file size in bytes. Maximum 500MB (524288000 bytes)
>
> **contentType** `string` *required*
>
> The MIME type of the file (e.g. "application/pdf", "image/png", "text/plain")

> [accordion] Get automation runs
>
> **Slug:** `MONDAY_MCP_GET_AUTOMATION_RUNS`
>
> Read automation/workflow run history. Read-only.
>
> Modes:
>
> * "history": paginated run feed (state, duration, error reason). Use "filters" to narrow results and "nextPageOffset" to page (offset-only — next page = previous offset + returned count).
> * "detail": single run by "triggerUuid" (required) — returns block steps and MCP tool calls. Set "includeToolEvents": false to skip tool calls.
>
> Scope: provide "boardId" for a specific board or "accountWide": true. One is required.
>
> Known event states: "success", "failure", "exhausted".
>
> #### Input Parameters
>
> **mode** `string ("history" | "detail")` *required*
>
> history = paginated run feed, detail = single run by triggerUuid
>
> **boardId** `string`
>
> Target a specific board by numeric ID
>
> **filters** `object`
>
> history: run filters
>
> **accountWide** `boolean`
>
> Set true to query account-wide (required if no boardId)
>
> **triggerUuid** `string`
>
> detail: required — the run UUID to inspect
>
> **nextPageOffset** `integer`
>
> history: page offset (offset-only pagination)
>
> **toolEventsOffset** `integer`
>
> detail: tool-events page offset
>
> **blockEventsOffset** `integer`
>
> detail: block-events page offset
>
> **includeToolEvents** `boolean`
>
> detail: include MCP tool calls (default true)

> [accordion] Get automation statistics
>
> **Slug:** `MONDAY_MCP_GET_AUTOMATION_STATISTICS`
>
> Aggregate automation run statistics. Read-only.
>
> Breakdowns:
>
> * "totals": success/failure/total counts at the account or board level.
> * "by\_entity": per-automation and per-workflow counts for a given "runStatus" (required: "success" | "failure" | "exhausted"). Use "excludeAutomationIds" to omit specific automations.
>
> Scope: provide "boardId" for a specific board or "accountWide": true. One is required.
>
> Optional "userIds" narrows results to specific creators.
>
> #### Input Parameters
>
> **boardId** `string`
>
> Target a specific board by numeric ID
>
> **userIds** `array`
>
> Narrow to specific creator user IDs
>
> **breakdown** `string ("totals" | "by_entity")` *required*
>
> totals = success/failure/total counts, by\_entity = per automation/workflow
>
> **runStatus** `string ("success" | "failure" | "exhausted")`
>
> by\_entity: required run status to break down
>
> **accountWide** `boolean`
>
> Set true to query account-wide (required if no boardId)
>
> **excludeAutomationIds** `array`
>
> by\_entity: automation IDs to exclude from breakdown

> [accordion] Get board activity
>
> **Slug:** `MONDAY_MCP_GET_BOARD_ACTIVITY`
>
> Get board activity logs for a specified time range (defaults to last 30 days). Optionally filter by item ids or user ids to avoid fetching activity for the entire board. \[REQUIRED PRECONDITION]: Call this with includeData=true before undo\_action — it is the source of the action\_record\_uuid that identifies the action to undo.
>
> #### Input Parameters
>
> **toDate** `string`
>
> End date for activity range (ISO8601DateTime format). Defaults to now
>
> **boardId** `number` *required*
>
> The id of the board to get activity for
>
> **itemIds** `array`
>
> Filter activity to specific item ids. Omit to get activity for the whole board.
>
> **userIds** `array`
>
> Filter activity to actions performed by specific user ids.
>
> **fromDate** `string`
>
> Start date for activity range (ISO8601DateTime format). Defaults to 30 days ago
>
> **includeData** `boolean`
>
> Whether to include the raw data payload for each activity entry. The data field contains the full before/after state of changes and can be very large. Only set to true when you need the detailed change data.

> [accordion] Get board info
>
> **Slug:** `MONDAY_MCP_GET_BOARD_INFO`
>
> Get comprehensive board information including metadata, structure, owners, and configuration. Also returns the board's views (e.g. table views, filter views) — each view includes its id, name, type, and a structured filter object. On large boards, ALWAYS narrow the response: use filters.views.names or filters.views.ids when you only need specific views, and/or filters.columns.ids when you only need specific columns. Set filters.views.only or filters.columns.only when you want just that section — full views\[].settings across many views can be multi-MB. The response includes hierarchy\_type which indicates if the board is a multi-level board ("multi\_level") where items can have nested subitems up to 5 levels deep on the same board. On multi-level boards, subitems share the same columns as parent items and subItemColumns will be null. Call this FIRST whenever you are not already familiar with a board structure (column IDs, column types, column revisions, status labels) — before reading or writing its data, or before any tool that declares this as a required precondition (e.g. get\_board\_items\_page, board\_insights, create\_item, create\_items, update\_items, change\_item\_column\_values, update\_column, create\_view, create\_view\_table, update\_view, update\_view\_table). Also use the views it returns to resolve a view referenced by name (pass that name in filters.views.names), and as the source of view ids for update\_view and update\_view\_table. Each column's "settings" field is the raw API value for that existing column, shown so you can read current labels/config — it is NOT the format expected by the columnSettings parameter of create\_column or update\_column. Never copy a column's "settings" object verbatim into columnSettings — use get\_column\_type\_info with fetchMode "schema" to get the correct shape for the column type you are creating or updating.
>
> #### Input Parameters
>
> **boardId** `number` *required*
>
> The id of the board to get information for
>
> **filters** `object`
>
> Optional response-shaping filters for large boards. Omit to return the full board info payload.

> [accordion] Get board items page
>
> **Slug:** `MONDAY_MCP_GET_BOARD_ITEMS_PAGE`
>
> Get all items from a monday.com board with pagination support and optional column values and item descriptions. Returns structured JSON with item details, creation/update timestamps, and pagination info. Use the nextCursor parameter from the response to get the next page of results when has\_more is true. To retrieve an item description (the rich-text body/details of a monday.com item), set includeItemDescription to true — the response will include the item description document blocks with their content, type, and id. Use this whenever the user asks about an item description, body, details, or notes. \[MULTI-LEVEL BOARDS]: The response includes hierarchy\_type on the board ("multi\_level" for MLS boards) and parent\_item\_id on each item. On multi-level boards, items form a tree (up to 5 levels). Use includeSubItems to get all descendants (returned flat with parent\_item\_id to reconstruct the tree). Top-level items have no parent\_item\_id. Subitems reference their parent. \[REQUIRED PRECONDITION]: Before using this tool, if new columns were added to the board or if you are not familiar with the board structure (column IDs, column types, status labels, etc.), first use get\_board\_info with filters.columns.only to get column metadata without fetching views. This is essential for constructing proper filters and knowing which columns are available. \[VIRTUAL COLUMNS]: Four filterable columns exist that get\_board\_info never returns - "group" (the item's board group), "**creation\_log**" (creation time), "**last\_updated**" (update time) and "**item\_id**" (item id). All four are also valid in orderBy, e.g. "**creation\_log**" with direction "desc" to sort newest-first. Call get\_column\_type\_info with the matching column type for each one's compareValue and operator rules. \[REQUIRED PRECONDITION]: For board-relation / cross-board linking tasks, call link\_board\_items\_workflow before using this tool. VIEW-BASED FILTERING: If the user refers to a board view by name (e.g. "show me items in the Overdue view"), first call get\_board\_info with filters.views.names set to that view name (avoids downloading all views on large boards), extract the matching view's filter field, then pass it as the filters argument here.
>
> #### Input Parameters
>
> **limit** `number`
>
> The number of items to get
>
> **cursor** `string`
>
> The cursor to get the next page of items, use the nextCursor from the previous response. If the nextCursor was null, it means there are no more items to get
>
> **boardId** `number` *required*
>
> The id of the board to get items from
>
> **filters** `array`
>
> The configuration of filters to apply on the items. Use get\_board\_info with filters.columns.only for column ids and types on the board. Before sending the filters, use get\_column\_type\_info with fetchMode "guidelines" and use data.guidelines.filter (null if that type has no documented rules).
>
> **itemIds** `array`
>
> The ids of the items to get. The count of items should be less than 100.
>
> **orderBy** `array`
>
> The columns to order by, will control the order of the items in the response
>
> **columnIds** `array`
>
> The ids of the item columns and subitem columns to get, can be used to reduce the response size when user asks for specific columns. Works only when includeColumns is true. If not provided, all columns will be returned
>
> **searchTerm** `string`
>
> The search term to use for the search.     - Use this when: the user provides a vague, incomplete, or approximate search term (e.g., “marketing campaign”, “John’s task”, “budget-related”), and there isn’t a clear exact compare value for a specific field.     - Do not use this when: the user specifies an exact value that maps directly to a column comparison (e.g., name contains "marketing campaign", status = "Done", priority = "High", owner = "Daniel"). In these cases, prefer structured compare filters.
>
> **includeGroup** `boolean`
>
> Whether to include each item's board group (id and title) in the response. Set to false to reduce token usage when group membership is not needed.
>
> **subItemLimit** `number`
>
> The number of sub items to get per item. This is only used when includeSubItems is true.
>
> **includeColumns** `boolean`
>
> Whether to include column values in the response. PERFORMANCE OPTIMIZATION: Only set this to true when you actually need the column data. Excluding columns significantly reduces token usage and improves response latency. If you only need to count items, get item IDs/names, or check if items exist, keep this false.
>
> **filtersOperator** `string ("and" | "or")`
>
> The operator to use for the filters
>
> **includeSubItems** `boolean`
>
> Whether to include sub items in the response. PERFORMANCE OPTIMIZATION: Only set this to true when you actually need the sub items data.
>
> **includeItemDescription** `boolean`
>
> Whether to include the item's description in the response. The item description is the rich-text body content that appears inside a monday.com item (similar to a task description or issue body). Set this to true when the user asks about an item's description, details, body, or notes. PERFORMANCE OPTIMIZATION: Only set this to true when you actually need the item description content.

> [accordion] Get column type info
>
> **Slug:** `MONDAY_MCP_GET_COLUMN_TYPE_INFO`
>
> Retrieves comprehensive information about a specific column type. Use fetchMode "schema" (default) to get the JSON schema definition from the API — to understand structure, validation rules, and available properties for column settings. Call this BEFORE any tool that writes column settings: create\_column, update\_column, and manage\_object\_schema\_columns. Use fetchMode "guidelines" to get only guidelines.filter and guidelines.aggregation (no schema, no GraphQL round-trip). Call this before building any filter rule that uses compare\_value/operator for that column type — e.g. get\_board\_items\_page, board\_insights, or a view's filters (create\_view, create\_view\_table, update\_view, update\_view\_table) — and before building board insights aggregation counts.
>
> #### Input Parameters
>
> **fetchMode** `string ("schema" | "guidelines")`
>
> fetchMode "schema": JSON settings schema only (GraphQL). fetchMode "guidelines": guidelines.filter and guidelines.aggregation only — no GraphQL round-trip.
>
> **columnType** `string ("auto_number" | "board_relation" | "button" | "checkbox" | "color_picker" | "country" | "creation_log" | "date" | "dependency" | "direct_doc" | "doc" | "dropdown" | "email" | "file" | "formula" | "group" | "hour" | "integration" | "item_assignees" | "item_id" | "last_updated" | "link" | "location" | "long_text" | "mirror" | "name" | "numbers" | "people" | "phone" | "progress" | "rating" | "status" | "subtasks" | "tags" | "team" | "text" | "time_tracking" | "timeline" | "unsupported" | "vote" | "week" | "world_clock")` *required*
>
> The column type to retrieve information for (e.g., "text", "status", "date", "numbers")

> [accordion] Get form
>
> **Slug:** `MONDAY_MCP_GET_FORM`
>
> Get a monday.com form by its form token, including its pages, questions, question ids, settings, and conditional showIfRules. Form tokens can be extracted from the form's url. Given a form url, such as [https://forms.monday.com/forms/abc123def456ghi789?r=use1](https://forms.monday.com/forms/abc123def456ghi789?r=use1), the formToken is the alphanumeric string that appears right after /forms/ and before the ?. In the example, the formToken is abc123def456ghi789. Call this FIRST before any tool that acts on an existing form: create\_form\_submission (to know the questions and their constraints), form\_questions\_editor (to resolve question ids and current structure), and update\_form (to see the current settings before changing them).
>
> #### Input Parameters
>
> **formToken** `string` *required*

> [accordion] Get graphql schema
>
> **Slug:** `MONDAY_MCP_GET_GRAPHQL_SCHEMA`
>
> Fetch the monday.com GraphQL schema structure including query and mutation definitions. This tool returns available query fields, mutation fields, and a list of GraphQL types in the schema. You can filter results by operation type (read/write) to focus on either queries or mutations.
>
> #### Input Parameters
>
> **operationType** `string ("read" | "write")`
>
> Type of operation: "read" for queries, "write" for mutations
>
> **random\_string** `string`
>
> Dummy parameter for no-parameter tools

> [accordion] Get meetings content
>
> **Slug:** `MONDAY_MCP_GET_MEETINGS_CONTENT`
>
> Fetch full content (summary, topics, action items, transcript) for meetings you already have ids for. Get those ids from explore\_meetings (topic/listing/browse) or search\_meetings\_content (passages) first — this tool is NOT for discovery or listing. Pass the ids with the include\_ flags for the content you need (defaults to the summary if none are set). Requested ids that are not returned are listed in `missing_ids` (not found, not accessible, or no completed recording); meetings whose content was dropped to keep the response within its size limit are listed in `content_omitted_ids`. The search param is a narrow case-insensitive substring fallback on title, participant name, or email — NOT topic/keyword search.
>
> #### Input Parameters
>
> **ids** `array`
>
> The meeting IDs to fetch, from explore\_meetings or search\_meetings\_content. Fetches them in one call.
>
> **access** `string ("OWN" | "SHARED_WITH_ME" | "SHARED_WITH_ACCOUNT" | "ALL")`
>
> Filter by access level. OWN: meetings the user participated in or invited the bot to. SHARED\_WITH\_ME: shared with the user or their team. SHARED\_WITH\_ACCOUNT: shared with the entire account. ALL: all accessible meetings. Defaults to ALL when fetching specific ids; without ids it excludes meetings shared only account-wide (pass access: ALL to include those).
>
> **search** `string`
>
> Narrow fallback only: case-insensitive substring match on title, attendee name, or email. NOT topic/keyword search and NOT for discovery — use explore\_meetings to find meetings.
>
> **include\_topics** `boolean`
>
> Include discussion topics and talking points for each meeting.
>
> **include\_summary** `boolean`
>
> Include the AI-generated summary for each meeting.
>
> **include\_transcript** `boolean`
>
> Include the full transcript for each meeting. Transcripts can be very large.
>
> **include\_action\_items** `boolean`
>
> Include action items for each meeting.

> [accordion] Get monday dev sprints boards
>
> **Slug:** `MONDAY_MCP_GET_MONDAY_DEV_SPRINTS_BOARDS`
>
> Discover monday-dev sprints boards and their associated tasks boards in your account.
>
> ## Purpose:
>
> Identifies and returns monday-dev sprints board IDs and tasks board IDs that you need to use with other monday-dev tools. This tool scans your recently used boards (up to 100) to find valid monday-dev sprint management boards.
>
> ## What it Returns:
>
> * Pairs of sprints boards and their corresponding tasks boards
> * Board IDs, names, and workspace information for each pair
> * The bidirectional relationship between each sprints board and its tasks board
>
> ## Note:
>
> Searches recently used boards (up to 100). If none found, ask user to provide board IDs manually.

> [accordion] Get monday knowledge
>
> **Slug:** `MONDAY_MCP_GET_MONDAY_KNOWLEDGE`
>
> Ask a question about monday.com and get an AI-generated answer from the official knowledge base.
>
> Use kind="general" for questions about using monday.com — features, automations, UI, help center, and settings. Returns cited source articles with links. Use kind="developer\_docs" for questions about the monday.com API — GraphQL queries and mutations, authentication, rate limits, webhooks, schema, API best practices, and building apps.
>
> Important: do not include PII data in the questions.
>
> #### Input Parameters
>
> **kind** `string ("developer_docs" | "general")` *required*
>
> The knowledge domain to search. Use "developer\_docs" for questions about the monday.com API — GraphQL queries and mutations, authentication, rate limits, webhooks, schema, API best practices, and building apps. Use "general" for questions about using monday.com — features, automations, UI, help center, and settings.
>
> **query** `string` *required*
>
> The question or topic to search for in the monday.com knowledge base.

> [accordion] Get run once trigger entities
>
> **Slug:** `MONDAY_MCP_GET_RUN_ONCE_TRIGGER_ENTITIES`
>
> Lists the concrete entities (items, boards, docs, ...) the workflow's trigger can be fired on, so the workflow can be run once on one of them.
>
> Use this tool:
>
> * ALWAYS before calling run\_workflow\_once, to learn whether the trigger needs an entity and which entities are available.
> * When the user asks what the workflow would be run on.
>
> Do NOT use this tool for a board automation, such as one create\_automation built: run-once applies to workflows only, and the id create\_automation returns is not a workflowObjectId. Tell the user to trigger that automation on the board instead.
>
> The tool does NOT modify the workflow and does NOT run anything. The response is a JSON object:
>
> * status "ok": "requiresEntity" tells you whether run\_workflow\_once needs a triggerPayload, and "entities" is a list of \{ label, value } candidates. Show the labels to the user and let them pick; pass the picked entity's "value" object verbatim as run\_workflow\_once's triggerPayload. An empty "entities" list while requiresEntity is true means there is nothing to run on — tell the user instead of guessing a payload.
> * status "failed": "message" explains why the entities could not be listed. Relay it; do not call run\_workflow\_once.
>
> #### Input Parameters
>
> **workflowDraftId** `integer`
>
> The identifier of a draft that belongs to the workflow object referenced by workflowObjectId. When omitted, it refers to the live version of the workflow.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] Get sprints metadata
>
> **Slug:** `MONDAY_MCP_GET_SPRINTS_METADATA`
>
> List the sprints of a monday-dev sprints board with their metadata.
>
> Returns comprehensive sprint metadata including:
>
> ## Data Retrieved:
>
> A table of sprints with the following information:
>
> * Sprint ID
> * Sprint Name
> * Sprint timeline (planned from/to dates)
> * Sprint completion status (completed/in-progress/planned)
> * Sprint start date (actual)
> * Sprint end date (actual)
> * Sprint activation status
> * Sprint summary document object ID
>
> ## Parameters:
>
> * **limit**: Number of sprints to retrieve (default: 25, max: 100)
>
> Requires the Main Sprints board ID of the monday-dev containing your sprints. If you do not already have it, call get\_monday\_dev\_sprints\_boards first to discover it.
>
> ## Call this before:
>
> * get\_sprint\_summary — this tool returns the Sprint IDs that get\_sprint\_summary requires. Never guess a sprint ID.
>
> #### Input Parameters
>
> **limit** `number`
>
> The number of sprints to retrieve (default: 25, max: 100)
>
> **sprintsBoardId** `number` *required*
>
> The ID of the monday-dev board containing the sprints

> [accordion] Get sprint summary
>
> **Slug:** `MONDAY_MCP_GET_SPRINT_SUMMARY`
>
> Get the complete summary and analysis of a sprint.
>
> ## Purpose:
>
> Unlock deep insights into completed sprint performance.
>
> The sprint summary content including:
>
> * **Scope Management**: Analysis of planned vs. unplanned tasks, scope creep
> * **Velocity & Performance**: Individual velocity, task completion rates, workload distribution per team member
> * **Task Distribution**: Breakdown of completed tasks by type (Feature, Bug, Tech Debt, Infrastructure, etc.)
> * **AI Recommendations**: Action items, process improvements, retrospective focus areas
>
> ## Requirements:
>
> * Sprint must be completed and must be created after 1/1/2025
> * Requires a sprintId. \[REQUIRED PRECONDITION]: call get\_sprints\_metadata first to list the sprints on the board and resolve the sprintId (and to confirm the sprint is completed). If you do not know the sprints board ID either, start with get\_monday\_dev\_sprints\_boards.
>
> ## Important Note:
>
> When viewing the section "Completed by Assignee", you'll see user IDs in the format "@user-12345678". the 8 digits after the @is the user ID. To retrieve the actual owner names, use the list\_users\_and\_teams tool with the user ID and set includeTeams=false for optimal performance.
>
> #### Input Parameters
>
> **sprintId** `number` *required*
>
> The ID of the sprint to get the summary for (e.g., "9123456789")

> [accordion] Get type details
>
> **Slug:** `MONDAY_MCP_GET_TYPE_DETAILS`
>
> Get detailed information about a specific GraphQL type from the monday.com API schema, including its fields, input fields, and enum values. Call this with a known type name to confirm its exact fields, arguments, and enum values before referencing that type in an operation for all\_monday\_api, all\_api\_read, or all\_api\_write, so the fields and arguments you send actually exist.
>
> #### Input Parameters
>
> **typeName** `string` *required*
>
> The name of the GraphQL type to get details for

> [accordion] Get updates
>
> **Slug:** `MONDAY_MCP_GET_UPDATES`
>
> Get updates (comments/posts) from a monday.com item or board. Specify objectId and objectType (Item or Board) to retrieve updates. For Board queries, you can filter by date range using fromDate and toDate (both required together, ISO8601 format). By default, Board queries return only board discussion. Set includeItemUpdates to true to also include updates on individual items. Returns update text, creator info, timestamps, and optionally replies and assets.
>
> #### Input Parameters
>
> **page** `number`
>
> Page number for pagination (default: 1)
>
> **limit** `number`
>
> Number of updates per page (default: 25, max: 100)
>
> **toDate** `string`
>
> End of date range filter (e.g. "2025-06-01" or "2025-06-01T23:59:59Z"). Must be used together with fromDate. Only supported for Board objectType.
>
> **fromDate** `string`
>
> Start of date range filter (e.g. "2025-01-01" or "2025-01-01T00:00:00Z"). Must be used together with toDate. Only supported for Board objectType.
>
> **objectId** `string` *required*
>
> The ID of the item or board to get updates from
>
> **objectType** `string ("Item" | "Board")` *required*
>
> Type of object for which objectId was provided
>
> **includeAssets** `boolean`
>
> Include file attachments in the response
>
> **includeReplies** `boolean`
>
> Include update replies in the response
>
> **includeItemUpdates** `boolean`
>
> When objectType is Board, also include updates on individual items. Defaults to false, returning only board discussion. Set to true to retrieve all updates on a board, including updates on individual items.

> [accordion] Get user context
>
> **Slug:** `MONDAY_MCP_GET_USER_CONTEXT`
>
> Fetch current user information, account information, and their relevant items (boards, docs, folders, workspaces, dashboards).
>
> Use this tool to:
>
> * Get context about who the current user is (id, name, title)
> * Get account info: plan tier, active member count, trial status, and active products
> * Get the number of active members in the account (returns active\_members\_count)
> * Discover user's favorite boards, folders, workspaces, and dashboards
> * Get user's most relevant boards based on visit frequency and recency
> * Get user's most relevant docs based on load frequency and recency
> * Get user's most relevant people based on interaction frequency and recency
> * Reduce the need for search requests by knowing user's commonly accessed items

> [accordion] Get workflow run once status
>
> **Slug:** `MONDAY_MCP_GET_WORKFLOW_RUN_ONCE_STATUS`
>
> Reports how a run started by run\_workflow\_once ended: whether it succeeded, and if not, which step failed and why.
>
> Call this after run\_workflow\_once, passing the "automationId" it returned. The tool does NOT modify the workflow and does NOT run anything.
>
> It answers immediately with whatever is known so far, so a run in progress is a normal answer, not a problem:
>
> * "isTerminal": false — the run has NOT finished. This is NOT a failure. Wait "retryAfterMs" milliseconds and call this tool again with the same arguments. Keep doing that until isTerminal is true. Never report an outcome to the user while isTerminal is false; say the run is still going.
> * "isTerminal": true — the run is over and "state" is its final outcome. Report it and stop calling.
>
> Trust "isTerminal" over your own reading of "state". "state" is one of:
>
> * "success" — every step ran without error.
> * "failure" — a step failed. "errorReason" and the failing entry in "blocks" say which and why.
> * "exhausted" — the run gave up after retrying a step too many times.
> * "stopped" — the run was stopped before finishing, so the remaining steps never ran.
> * "zero\_actions" — the trigger fired but the workflow's conditions matched nothing, so no step ran. Nothing is broken; the entity did not qualify.
> * "running" — a step is executing right now.
> * "waiting" — the run is parked on a wait step or waiting for a second event. This can last hours, which is why "retryAfterMs" is long here. Tell the user it is waiting rather than polling silently for hours.
> * "not\_indexed\_yet" — the run's record has not appeared yet, which is expected for the first few seconds after a run starts. It does NOT mean nothing ran.
>
> "blocks" lists the steps recorded so far, each with its own "state" and, when it failed, "errorReason". While isTerminal is false this list is partial and is progress, not a verdict. Use it to tell the user which step failed rather than only that the run failed.
>
> The response is a JSON object:
>
> * status "ok": the fields above.
> * status "failed": the status could not be read. "message" explains why. This says nothing about the run itself — do not report the run as failed because of it.
>
> #### Input Parameters
>
> **automationId** `integer`
>
> The "automationId" that run\_workflow\_once returned for the run you are asking about. Omit it only if you no longer have it — the status of the workflow's most recent run is then returned, which may be a run someone else started.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] Invoke process planner
>
> **Slug:** `MONDAY_MCP_INVOKE_PROCESS_PLANNER`
>
> A reasoning-focused process planner with deep knowledge of monday.com workflow architecture. Given a description of a process, it returns a structured textual plan describing one or more related workflows that implement it.
>
> Use this tool for:
>
> * Planning a new workflow or multi-workflow architecture from a process description.
> * Deciding whether a process should be implemented as a single workflow or multiple related workflows.
> * Producing a concrete, block-level plan (trigger, steps, route keys) that another agent or human can build from.
> * Don't tell it about one time actions, like non-repeating resource creations that are needed to set up the process.
>
> This tool does NOT have access to any specific workflow's current state — it plans from scratch using all available blocks. It does not execute any changes.
>
> #### Input Parameters
>
> **prompt** `string` *required*
>
> A description of the process to plan. The planner will design one or more related workflows that implement it, using only the blocks available in the system.

> [accordion] Invoke workflow expert
>
> **Slug:** `MONDAY_MCP_INVOKE_WORKFLOW_EXPERT`
>
> Workflow expert for a single workflow. Given a prompt, answers questions about the workflow's structure and configuration, or makes changes to it (create, update, delete steps, and configure step fields).
>
> Delegate any prompt that asks about a workflow or asks to change it. Pass clear, descriptive instructions — the expert will decide the right response or operations.
>
> Field values reference resources (boards, columns, people, channels, projects, ...) from monday or any external app — all handled the same way. Pass each resource through as the user stated it; the expert resolves names to IDs and asks the user when it's ambiguous. Pro-tip: pass along any ID you already have to save a follow-up question — no need to look one up first.
>
> Constraints: works on ONE workflow at a time.
>
> #### Input Parameters
>
> **prompt** `string` *required*
>
> A question about the workflow or a description of the changes to make to it
>
> **workflowDraftId** `integer`
>
> The identifier of a draft that belongs to the workflow object referenced by workflowObjectId. When omitted, it refers to the live version of the workflow.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] List actions
>
> **Slug:** `MONDAY_MCP_LIST_ACTIONS`
>
> List all saved actions for the current user.

> [accordion] List automations
>
> **Slug:** `MONDAY_MCP_LIST_AUTOMATIONS`
>
> List all automations on a specific monday.com board, including their ids, titles, active state, and configuration. Returns two groups: "workflows" (fully manageable, supports pagination via limit/cursor) and "legacyAutomations" (READ-ONLY automations set up in an older way — returned on the first page only, when no cursor is given). Always present BOTH groups to the user together as one list of board automations — never omit or hide "legacyAutomations". The split and the read-only limitation are internal context for you only: don't volunteer them and don't label any automation "legacy" or "read-only". Only if the user asks to act on a legacy one, briefly explain it can't be changed (e.g. "This one was set up in an older way and can't be modified here"). Call this FIRST before manage\_automations — it is the only way to resolve an automation id from a name or description. Never guess an automation id. When NOT to use: Do not call this tool to get general board information unrelated to automations.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of automations to return. Default: 100.
>
> **cursor** `string`
>
> Pagination cursor from a previous response. Pass to retrieve the next page of automations.
>
> **boardId** `string` *required*
>
> The numeric board ID as a string.

> [accordion] List users and teams
>
> **Slug:** `MONDAY_MCP_LIST_USERS_AND_TEAMS`
>
> Tool to fetch users and/or teams data.
>
> MANDATORY BEST PRACTICES:
>
> 1. ALWAYS use specific IDs or names when available
> 2. If no ids available, use name search if possible (USERS ONLY)
> 3. Use 'getMe: true' to get current user information
> 4. AVOID broad queries (no parameters) - use only as last resort
>
> REQUIRED PARAMETER PRIORITY (use in this order):
>
> 1. getMe - STANDALONE
> 2. userIds
> 3. name - STANDALONE (USERS ONLY, NOT for teams)
> 4. teamIds + teamsOnly
> 5. No parameters - LAST RESORT
>
> CRITICAL USAGE RULES: • userIds + teamIds requires explicit includeTeams: true flag • includeTeams: true fetches both users and teams, do not use this to fetch a specific user's teams rather fetch that user by id and you will get their team memberships. • name parameter is for USER search ONLY - it cannot be used to search for teams. Use teamIds to fetch specific teams.
>
> #### Input Parameters
>
> **name** `string`
>
> Name-based USER search ONLY. STANDALONE parameter - cannot be combined with others. PREFERRED method for finding users when you know names. Performs fuzzy matching.       CRITICAL: This parameter searches for USERS ONLY, NOT teams. To search for teams, use teamIds parameter instead.
>
> **getMe** `boolean`
>
> \[TOP PRIORITY] Use ALWAYS when requesting current user information. Examples of when it should be used: \["get my user" or "get my teams"].       This parameter CONFLICTS with all others.
>
> **teamIds** `array`
>
> Specific team IDs to fetch.\[IMPORTANT] ALWAYS use when you have team IDs in context, NEVER fetch all teams if specific IDs are available.       RETURNS: Team details with owners and optional member data.
>
> **userIds** `array`
>
> Specific user IDs to fetch.\[IMPORTANT] ALWAYS use when you have user IDs in context. PREFER over general search. RETURNS: user profiles including team memberships
>
> **teamsOnly** `boolean`
>
> Fetch only teams, no users returned. Combine with includeTeamMembers for member details.
>
> **includeTeams** `boolean`
>
> \[AVOID] This fetches all teams in the account. To fetch a specific user's teams just fetch that user by id and you will get their team memberships.
>
> **includeTeamMembers** `boolean`
>
> Set to true only when you need additional member details for teams other than names and ids.

> [accordion] List workspaces
>
> **Slug:** `MONDAY_MCP_LIST_WORKSPACES`
>
> List all workspaces available to the user, ordered by membership (user's workspaces first). Returns workspaces with their ID, name, and description. \[IMPORTANT] To search for workspaces by name, use the "search" tool with searchType WORKSPACES instead — it provides faster and more accurate results.
>
> #### Input Parameters
>
> **page** `number`
>
> Page number to return. Default is 1.
>
> **limit** `number`
>
> Number of workspaces to return. Default is (100), lower for a smaller response size

> [accordion] Manage agent
>
> **Slug:** `MONDAY_MCP_MANAGE_AGENT`
>
> Full lifecycle management for monday platform agents — create, read, update, delete, change state, and run.
>
> monday platform agents are user-built work orchestrators on monday.com. Each has a profile, goal, and agent-level Identity. Jobs define specific work, instructions, and triggers. Agents in state ACTIVE can be triggered automatically. They are NOT local LangChain or MCP agents.
>
> ACTIONS (only pass fields that apply to the chosen action):
>
> * create:        \{ action:"create", prompt, identity?, agent\_model? } — AI-generated agent. Platform creates profile, goal, and Identity from the prompt unless identity is supplied.
> * create\_blank:  \{ action:"create\_blank", name?, role?, role\_description?, avatar\_url?, gender?, background\_color?, user\_prompt? } — manually defined agent.
> * get one:       \{ action:"get", agent\_id }
> * list owned:    \{ action:"get" }
> * update:        \{ action:"update", agent\_id, name?, role?, role\_description?, identity?, plan?, agent\_model? }
> * delete:        \{ action:"delete", agent\_id }
> * activate:      \{ action:"activate", agent\_id }
> * deactivate:    \{ action:"deactivate", agent\_id }
> * run:           \{ action:"run", agent\_id }
>
> RULES:
>
> * "create\_blank" with no fields creates a nameless blank agent — only do this intentionally.
> * "update" requires at least one of name/role/role\_description/identity/plan/agent\_model.
> * Do not put job-specific instructions in Identity. Configure them with manage\_agent\_jobs.
> * "update", "delete", "activate", "deactivate", "run" all require "agent\_id".
> * Created agents start INACTIVE. Follow with action:"activate" using the returned agent\_id before they can be triggered.
> * ⚠️ DESTRUCTIVE — "delete" is permanent and irreversible. When the user refers to an agent by name, ALWAYS call action:"get" first to confirm the correct agent\_id before deleting.
> * "run" is fire-and-forget. Returns trigger\_uuid — no run-status query exists, treat successful enqueue as the only signal.
> * Agent state is one of ACTIVE, INACTIVE, ARCHIVED, or FAILED. DELETED only appears as the return value of action:"delete".
>
> USAGE EXAMPLES:
>
> * AI create:    \{ "action": "create", "prompt": "Run my daily standup every weekday at 9am." }
> * Manual create:\{ "action": "create\_blank", "name": "Standup Bot", "role": "Project Manager", "gender": "female" }
> * Fetch one:    \{ "action": "get", "agent\_id": "42" }
> * List mine:    \{ "action": "get" }
> * Rename:       \{ "action": "update", "agent\_id": "7", "name": "New Name" }
> * Activate:     \{ "action": "activate", "agent\_id": "7" }
> * Deactivate:   \{ "action": "deactivate", "agent\_id": "7" }
> * Run:          \{ "action": "run", "agent\_id": "7" }
> * Delete:       \{ "action": "delete", "agent\_id": "7" }
>
> RELATED TOOLS:
>
> * agent\_catalog — browse available trigger types and skills before wiring them to an agent
> * manage\_agent\_jobs — configure jobs, job instructions, and nested triggers
> * manage\_agent\_triggers — manage which triggers fire this agent automatically
> * manage\_agent\_skills — manage which skills this agent can perform
> * manage\_agent\_knowledge — manage which boards/docs this agent has access to
>
> #### Input Parameters
>
> **name** `string`
>
> Used with action:"create\_blank" or action:"update". Display name of the agent.
>
> **plan** `string`
>
> Legacy alias for identity. Used with action:"update".
>
> **role** `string`
>
> Used with action:"create\_blank" or action:"update". Short role title (e.g. "Customer Success Bot").
>
> **action** `string ("create" | "create_blank" | "get" | "update" | "delete" | "activate" | "deactivate" | "run")` *required*
>
> "create" — create a new agent via AI (pass prompt). "create\_blank" — create a new agent manually (pass name/role/etc). "get" — fetch one agent by agent\_id or list owned agents. "update" — modify mutable fields on an existing agent. "delete" — permanently delete an agent (irreversible). "activate" — transition agent to ACTIVE. "deactivate" — transition agent to INACTIVE. "run" — manually enqueue an agent run (fire-and-forget).
>
> **gender** `string ("male" | "female")`
>
> Used with action:"create\_blank". Hint for generated avatar/name when profile fields are omitted.
>
> **prompt** `string`
>
> Required for action:"create". Plain-language description of what the agent should do. Platform generates profile, goal, and Identity via AI.
>
> **agent\_id** `string`
>
> Used with action:"get" to fetch a specific agent. Required for action:"update", "delete", "activate", "deactivate", "run". Omit for action:"create", "create\_blank", or action:"get" (to list owned agents).
>
> **identity** `string`
>
> Used with action:"create" or action:"update" when agent jobs with instructions are enabled. Agent-level Identity, tone, and guardrails in markdown; job-specific work belongs in manage\_agent\_jobs.
>
> **avatar\_url** `string`
>
> Used with action:"create\_blank". HTTPS URL of the avatar. Prefer dapulse-res.cloudinary.com or cdn.monday.com.
>
> **agent\_model** `string ("CLAUDE_SONNET_4_6" | "CLAUDE_OPUS_4_7" | "CLAUDE_SONNET_5" | "CLAUDE_OPUS_5" | "CLAUDE_FABLE_5" | "GPT_5_2" | "GPT_5_6" | "GPT_5_6_LUNA" | "GPT_5_6_SOL" | "GPT_6_ASTRA" | "GEMINI_3_8_FLASH" | "GEMINI_3_7_FLASH" | "GEMINI_3_5_FLASH_LITE" | "GEMINI_2_5_FLASH")`
>
> Used with action:"create" or action:"update". Omit unless the user explicitly names a valid monday-supported model.
>
> **user\_prompt** `string`
>
> Used with action:"create\_blank". Stored as metadata. Not used for AI generation.
>
> **background\_color** `string`
>
> Used with action:"create\_blank". Lowercase hex, e.g. "#9450fd".
>
> **role\_description** `string`
>
> Used with action:"create\_blank" or action:"update". Detailed description of the agent role.

> [accordion] Manage agent knowledge
>
> **Slug:** `MONDAY_MCP_MANAGE_AGENT_KNOWLEDGE`
>
> List, grant, update, or revoke a monday platform agent's access to boards and docs.
>
> An agent's "knowledge" is the set of monday.com boards and docs it can read from or write to during a run.
>
> * list: Returns all resources the agent currently has access to, including permission level and resource type.
> * add: Grants the agent access to a board or doc with the specified permission level.
> * update: Changes the permission level on a resource the agent already has access to. Call action:"list" first to confirm the resource\_id exists.
> * remove: Revokes the agent's access to a board or doc entirely. Call action:"list" first to confirm the resource\_id exists.
>
> Permission types:
>
> * READ: Agent can read data from the resource.
> * READ\_WRITE: Agent can read and write data to the resource.
>
> USAGE EXAMPLES:
>
> * List: \{ "action": "list", "agent\_id": "7" }
> * Add board access: \{ "action": "add", "agent\_id": "7", "resource\_id": "42", "scope\_type": "BOARD", "permission\_type": "READ" }
> * Update to read-write: \{ "action": "update", "agent\_id": "7", "resource\_id": "42", "scope\_type": "BOARD", "permission\_type": "READ\_WRITE" }
> * Remove access: \{ "action": "remove", "agent\_id": "7", "resource\_id": "42", "scope\_type": "BOARD" }
>
> RELATED TOOLS:
>
> * manage\_agent — manage the agent entity itself (create, activate, deactivate, etc.)
> * manage\_agent\_triggers — manage which triggers fire this agent automatically
> * manage\_agent\_skills — manage which skills this agent can perform
>
> #### Input Parameters
>
> **action** `string ("list" | "add" | "update" | "remove")` *required*
>
> "list" — returns all resources the agent currently has access to. "add" — grants access to a board or doc. "update" — changes the permission level on an existing resource. "remove" — revokes the agent's access to a board or doc.
>
> **agent\_id** `string` *required*
>
> Unique identifier of the agent.
>
> **scope\_type** `string ("BOARD" | "DOC")`
>
> Required for action:add, action:update, action:remove. The type of resource: "BOARD" or "DOC".
>
> **resource\_id** `string`
>
> Required for action:add, action:update, action:remove. The ID of the board or doc to grant/update/revoke access to.
>
> **permission\_type** `string ("READ" | "READ_WRITE")`
>
> Required for action:add and action:update. The permission level: "READ" (agent can read the resource) or "READ\_WRITE" (agent can read and write the resource).

> [accordion] Manage agent skills
>
> **Slug:** `MONDAY_MCP_MANAGE_AGENT_SKILLS`
>
> Manage the full skill lifecycle for monday platform agents — create new skills in the catalog, attach skills to an agent, or detach them.
>
> Skills extend what an agent can do (e.g. sending emails, querying databases, posting to Slack).
>
> ACTIONS:
>
> * create: \{ name, content, description? } — creates a new custom skill in the account-wide catalog. The skill becomes available to all agents in the account.
> * add:    \{ agent\_id, skill\_id } — attaches a skill to this agent.
> * remove: \{ agent\_id, skill\_id } — detaches a skill from this agent.
>
> WORKFLOW — attach an existing skill:
>
> 1. Call agent\_catalog action:"list\_skills" — find the skill\_id of the skill to attach.
> 2. Call this tool action:"add" with agent\_id and that skill\_id.
>
> WORKFLOW — create a new skill and attach it:
>
> 1. Call this tool action:"create" with name and content — note the returned id.
> 2. Call this tool action:"add" with agent\_id and that id directly (no catalog lookup needed).
>
> NOTE: There is no action to list which skills are currently attached to a specific agent — the platform does not yet expose that query. To browse all skills available in the account catalog, use agent\_catalog action:"list\_skills".
>
> USAGE EXAMPLES:
>
> * Create a skill:  \{ "action": "create", "name": "Send Slack Message", "content": "## Instructions\nPost a message to a Slack channel.", "description": "Sends a message to Slack" }
> * Add a skill:     \{ "action": "add", "agent\_id": "7", "skill\_id": "skill-abc-123" }
> * Remove a skill:  \{ "action": "remove", "agent\_id": "7", "skill\_id": "skill-abc-123" }
>
> RELATED TOOLS:
>
> * agent\_catalog action:"list\_skills" — browse existing skills to find a skill\_id before calling action:"add"
> * manage\_agent\_triggers — manage which triggers fire this agent automatically
> * manage\_agent — manage the agent entity itself (create, activate, deactivate, etc.)
>
> #### Input Parameters
>
> **name** `string`
>
> Required for action:"create". Display name of the new skill.
>
> **action** `string ("create" | "add" | "remove")` *required*
>
> "create" — author a new custom skill in the account-wide catalog (no agent\_id needed). "add" — attach an existing skill to this agent by skill\_id. "remove" — detach a skill from this agent.
>
> **content** `string`
>
> Required for action:"create". Markdown instructions defining what the skill does and how to execute it. Be specific and thorough — this is the skill's runtime behavior.
>
> **agent\_id** `string`
>
> Required for action:"add" and action:"remove". Not used for action:"create" (account-level operation).
>
> **skill\_id** `string`
>
> Required for action:"add" and action:"remove". The skill id from agent\_catalog action:"list\_skills", or the id returned by action:"create" in this tool. Never guess or invent a skill id.
>
> **description** `string`
>
> Used with action:"create". Short description shown in the catalog.

> [accordion] Manage agent triggers
>
> **Slug:** `MONDAY_MCP_MANAGE_AGENT_TRIGGERS`
>
> Legacy flat-trigger management for a monday platform agent. When jobs with instructions are enabled, use manage\_agent\_jobs so each trigger belongs to an explicit job.
>
> ACTIONS:
>
> * list:   \{ agent\_id } — returns active triggers with node\_id, block\_reference\_id, name, field\_summary.
> * add:    \{ agent\_id, block\_reference\_id, field\_values? } — attaches a trigger type to the agent.
> * remove: \{ agent\_id, node\_id } — detaches a trigger instance by node\_id (NOT block\_reference\_id).
>
> WORKFLOW — add a trigger:
>
> 1. Call agent\_catalog action:"list\_triggers" — note block\_reference\_id, field\_schemas, and required\_fields.
> 2. Collect required field values from the user (e.g. board\_id, column\_id).
> 3. Call this tool action:"add" with block\_reference\_id and field\_values. Note: add returns only \{ success } — no node\_id for the new instance. Call action:"list" afterward if you need the node\_id.
>
> WORKFLOW — remove a trigger:
>
> 1. Call action:"list" to see active triggers and note the node\_id of the instance to remove.
> 2. Call action:"remove" with that node\_id.
>
> NOTE: Only triggers that can be added programmatically appear in the catalog. OAuth/3rd-party triggers (Slack, Gmail, Salesforce, etc.) require user setup in the monday.com UI — they will not appear in agent\_catalog and cannot be managed here.
>
> USAGE EXAMPLES:
>
> * List triggers:  \{ "action": "list", "agent\_id": "7" }
> * Add trigger:    \{ "action": "add", "agent\_id": "7", "block\_reference\_id": "status-change-ref", "field\_values": \{ "board\_id": "42" } }
> * Remove trigger: \{ "action": "remove", "agent\_id": "7", "node\_id": "node-abc" }
>
> RELATED TOOLS:
>
> * manage\_agent\_jobs — jobs-aware configuration with per-job instructions and nested triggers
> * agent\_catalog action:"list\_triggers" — discover available trigger types and their required field\_values before calling action:"add" here
> * manage\_agent\_skills — manage which skills this agent can perform
> * manage\_agent — manage the agent entity itself (create, activate, deactivate, etc.)
>
> #### Input Parameters
>
> **action** `string ("list" | "add" | "remove")` *required*
>
> "list" — returns all triggers currently attached to this agent (includes node\_id needed for remove). "add" — attaches a new trigger by block\_reference\_id. "remove" — detaches a trigger instance by node\_id.
>
> **node\_id** `string`
>
> Required for action:"remove". The node\_id of the trigger instance — get it from action:"list". Each instance has a unique node\_id even if the same trigger type is attached multiple times. Do NOT pass block\_reference\_id here.
>
> **agent\_id** `string` *required*
>
> Unique identifier of the agent.
>
> **field\_values** `object`
>
> Used with action:"add" when the trigger type has required\_fields. Key/value object whose shape is described by field\_schemas in the agent\_catalog response. Scalar fields use string/number/boolean values. Selection fields use \{ "value": "\<id>", "label": "\<name>" }.
>
> **block\_reference\_id** `string`
>
> Required for action:"add". The block\_reference\_id from agent\_catalog action:"list\_triggers" identifying the trigger type to attach. Never guess this value — look it up in the catalog first.

> [accordion] Manage automations
>
> **Slug:** `MONDAY_MCP_MANAGE_AUTOMATIONS`
>
> Activate, deactivate, or delete an existing monday.com automation.
>
> Requires an automation id. When the user refers to an automation by name, always call list\_automations first to resolve the id — never guess or infer ids.
>
> Actions:
>
> * activate: enables a paused automation so it starts responding to its trigger.
> * deactivate: pauses an automation while preserving its definition.
> * delete: permanently removes an automation — irreversible.
>
> When intent is ambiguous ("stop", "turn off", "pause"), prefer deactivate over delete.
>
> #### Input Parameters
>
> **action** `string ("activate" | "deactivate" | "delete")` *required*
>
> The operation to perform. activate: enables a paused automation so it responds to its trigger. deactivate: pauses an automation without deleting it. delete: permanently removes an automation (irreversible).
>
> **workflowId** `string` *required*
>
> The automation ID to operate on. Obtain from list\_automations.

> [accordion] Move object
>
> **Slug:** `MONDAY_MCP_MOVE_OBJECT`
>
> Move a folder, board, or overview in monday.com. Use position for relative placement based on another object, parentFolderId for folder changes, workspaceId for workspace moves, and accountProductId for account product changes.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The ID of the object to move
>
> **objectType** `string ("Board" | "Folder" | "Overview")` *required*
>
> The type of object to move
>
> **workspaceId** `string`
>
> The ID of the workspace containing the object. Required if moving to a different workspace.
>
> **parentFolderId** `string`
>
> The ID of the new parent folder. Required if moving to a different folder.
>
> **accountProductId** `string`
>
> The ID of the account product containing the object. Required if moving to a different account product.
>
> **position\_is\_after** `boolean`
>
> Whether to position the object after the object
>
> **position\_object\_id** `string`
>
> The ID of the object to position the object relative to. If this parameter is provided, position\_object\_type must be also provided.
>
> **position\_object\_type** `string ("Board" | "Folder" | "Overview")`
>
> The type of object to position the object relative to. If this parameter is provided, position\_object\_id must be also provided.

> [accordion] Publish workflow
>
> **Slug:** `MONDAY_MCP_PUBLISH_WORKFLOW`
>
> Promotes a workflow draft to live and optionally activates it.
>
> Use this tool when the user asks to publish, go live, or activate a workflow. The workflow is validated before publishing; if it has unresolved validation issues, the tool returns those issues instead of publishing, so they can be reported back to the user and fixed first.
>
> On success, the tool returns a JSON object with the workflowObjectId and the resulting workflowLiveId.
>
> #### Input Parameters
>
> **shouldActivate** `boolean`
>
> Activate the workflow immediately after publishing (defaults to true)
>
> **workflowDraftId** `integer` *required*
>
> The identifier of a draft that belongs to the workflow object referenced by workflowObjectId.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] Read docs
>
> **Slug:** `MONDAY_MCP_READ_DOCS`
>
> Get information about monday.com documents. Supports two modes:
>
> MODE: "content" (default) — Fetch documents with their full markdown content.
>
> * Requires: type ("ids" | "object\_ids" | "workspace\_ids") and ids array
> * Supports pagination via page/limit. Check has\_more\_pages in response.
> * If type "ids" returns no results, automatically retries with object\_ids.
> * Set include\_blocks: true to include block IDs, types, and positions in the response — required before calling update\_doc.
> * Blocks default to 25 per page. Use blocks\_limit and blocks\_page to paginate through long documents.
> * Set include\_comments: true to fetch all comments and replies on the document. Each comment is enriched with anchor info (block\_id, selection\_from, selection\_length) indicating which block and text range it's attached to. Use comments\_limit to control how many comments per item (default 50).
>
> MODE: "version\_history" — Fetch the edit history of a single document.
>
> * Requires: ids with the document's object\_id (use the object\_id field from content mode results, NOT the id field).
> * The object\_id is the numeric ID visible in the document URL.
> * Returns restoring points sorted newest-first. Use version\_history\_limit to cap results (e.g., "last 3 changes" → version\_history\_limit: 3).
> * Use since/until to filter by time range. If omitted, returns full history.
> * Set include\_diff: true to see what content changed between versions (fetches up to 10 diffs, may be slower).
> * Examples:
>   * \{ mode: "version\_history", ids: \["5001466606"], version\_history\_limit: 3 }
>   * \{ mode: "version\_history", ids: \["5001466606"], since: "2026-03-11T00:00:00Z", include\_diff: true }
>
> #### Input Parameters
>
> **ids** `array`
>
> Array of ID values. In content mode: matches the query type (ids/object\_ids/workspace\_ids). In version\_history mode: provide the single document object\_id here (e.g., ids: \["5001466606"]).
>
> **mode** `string ("content" | "version_history")`
>
> The operation mode. "content" (default) fetches documents with their markdown content. "version\_history" fetches the edit history of a single document.
>
> **page** `number`
>
> Page number to return (starts at 1). Only used in content mode.
>
> **type** `string ("ids" | "object_ids" | "workspace_ids")`
>
> Query type for content mode: "ids", "object\_ids", or "workspace\_ids". Required when mode is "content".
>
> **limit** `number`
>
> Number of docs per page (default: 25). Only used in content mode.
>
> **since** `string`
>
> ISO 8601 date string to filter version history from (e.g., "2026-03-15T00:00:00Z"). If omitted, returns the full history. Only used in version\_history mode.
>
> **until** `string`
>
> ISO 8601 date string to filter version history until (e.g., "2026-03-16T23:59:59Z"). Defaults to now. Only used in version\_history mode.
>
> **order\_by** `string ("created_at" | "used_at")`
>
> Order in which to retrieve docs. Only used in content mode.
>
> **blocks\_page** `number`
>
> Page number for block pagination, starting at 1. Omit to use the API default. Use with blocks\_limit to page through documents with more than 25 blocks. Only used in content mode when include\_blocks is true.
>
> **blocks\_limit** `number`
>
> Maximum number of blocks to return per document (default: 25). Only used in content mode when include\_blocks is true.
>
> **include\_diff** `boolean`
>
> If true, fetches content diffs between consecutive restoring points. May be slower due to additional API calls. Only used in version\_history mode.
>
> **comments\_limit** `number`
>
> Maximum number of comments (updates) to fetch per item when include\_comments is true. Defaults to 50. Only used in content mode.
>
> **include\_blocks** `boolean`
>
> If true, includes the blocks array (block IDs, types, positions, content) in the response. Required when you plan to call update\_doc. Defaults to false to reduce response size. Only used in content mode.
>
> **include\_comments** `boolean`
>
> If true, fetches all comments and replies on the document. Comments are stored at the item level within the doc backing board. Defaults to false. Only used in content mode.
>
> **version\_history\_limit** `number`
>
> Maximum number of restoring points to return. Use this when the user asks for "last N changes". Only used in version\_history mode.

> [accordion] Run action
>
> **Slug:** `MONDAY_MCP_RUN_ACTION`
>
> Execute a saved action by ID. Optionally pass variables (injected as environment variables, access via os.environ).
>
> Example: id: "abc-123", vars: \{"board\_id": 12345, "limit": 5}
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Action ID
>
> **vars** `object`
>
> Variables injected as environment variables into the sandbox (access via os.environ / process.env)

> [accordion] Run workflow once
>
> **Slug:** `MONDAY_MCP_RUN_WORKFLOW_ONCE`
>
> Runs the workflow once: a single execution, right now, on one real entity, without publishing or activating the workflow. When workflowDraftId is given the draft revision runs; otherwise the published live revision runs.
>
> THIS PERFORMS REAL SIDE EFFECTS. The blocks act on real boards, items and third-party apps: items get created and updated, notifications and emails go out, external systems are called. Nothing is simulated and nothing is rolled back.
>
> Required sequence — do not skip a step:
>
> 1. Call get\_run\_once\_trigger\_entities and show the user the entity labels.
> 2. Ask the user to confirm the run explicitly, naming the entity it will run on and warning that the effects are real. Never run on your own initiative, and never pick the entity for the user.
> 3. Only after the user confirms, call this tool with that entity's "value" as triggerPayload (omit triggerPayload when get\_run\_once\_trigger\_entities reported requiresEntity: false).
>
> The response is a JSON object:
>
> * status "running": the run was accepted and is now executing. You do not know its outcome yet, so never claim it succeeded, failed, or what it produced. Call get\_workflow\_run\_once\_status with the "automationId" from this response to find out; the user can also watch per-step progress in the builder UI.
> * status "validation\_failed": the draft is not fully configured, so nothing ran. "issues" lists what to fix; help the user fix them, then start over from step 1.
> * status "failed": the run could not be started. "message" explains why — commonly this workflow's trigger cannot be run once. Relay the message; do not retry blindly.
>
> #### Input Parameters
>
> **triggerPayload** `object`
>
> The entity the run should be triggered on. Pass the exact "value" object of the entity chosen from get\_run\_once\_trigger\_entities, unaltered. Omit it only when get\_run\_once\_trigger\_entities reported requiresEntity: false.
>
> **workflowDraftId** `integer`
>
> The identifier of a draft that belongs to the workflow object referenced by workflowObjectId. When omitted, it refers to the live version of the workflow.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] Search
>
> **Slug:** `MONDAY_MCP_SEARCH`
>
> Search within monday.com platform. Supported searchType values: BOARD, DOCUMENTS, FOLDERS, WORKSPACES, UPDATES, ITEMS, TIMELINE\_ITEMS, DASHBOARDS. searchTerm is the phrase the search matches against — the text/keywords to look for (e.g. a board name, item title, or a word from an update). It is required and must be non-empty. This tool has no "list everything" mode: to browse or list without a search phrase, use workspace\_info (boards/docs/folders in a workspace) or get\_board\_items\_page (items in a board) instead of calling search with an empty searchTerm. For searching/listing specific users and teams, use list\_users\_and\_teams tool. For account-level info (plan, member count, products), use get\_user\_context tool. For browsing all boards, docs, or folders within a workspace without a search term, use workspace\_info tool. For groups, use get\_board\_info tool. For listing items within a specific board, use get\_board\_items\_page tool. ITEMS search here queries items across the account. BOARD search returns id, title, url, and workspaceId. Optionally scope it with boardIds. DOCUMENTS search returns id, title, workspaceId, and highlights. highlights is an array of \{ field, fragments } entries (field is "name" or "content") where fragments contain matched text snippets with \<em> tags around matched terms. highlights is omitted when no lexical match was made. Optionally scope it with workspaceIds and/or docIds. ITEMS search returns id, title, url, boardId, and workspaceId. Optionally scope it with workspaceIds, boardIds, and/or creatorIds. WORKSPACES search returns id, title, and description. UPDATES search returns id, title (the update body), itemId, boardId, and creatorId. Optionally scope it with workspaceIds, boardIds, and/or creatorIds. TIMELINE\_ITEMS search returns id, title, summary, content, itemId, and boardId. Optionally scope it with workspaceIds and/or boardIds. DASHBOARDS search (also called "overviews") returns id, title, and workspaceId. Optionally scope it with workspaceIds and/or creatorIds. FOLDERS search returns id and title. Optionally scope it with workspaceIds, which searches all accessible workspaces when omitted. Pass workspaceIds to narrow the search if results may be truncated.
>
> #### Input Parameters
>
> **limit** `number`
>
> The number of items to get. Maximum is 20.
>
> **docIds** `array`
>
> Array of document IDs (numbers), as they appear in document URLs, to scope the search to. Applies to DOCUMENTS search, with at most 512 ids. Use it to search within a known set of documents, for example to find which of them mention a term. Only pass it if the user explicitly asked to search within specific documents. Example: \[12345, 67890].
>
> **boardIds** `array`
>
> Array of board IDs (numbers) to scope the search to. Applies to BOARD, ITEMS, UPDATES, and TIMELINE\_ITEMS search. Only pass it if the user explicitly asked to search within specific boards. Example: \[12345, 67890].
>
> **creatorIds** `array`
>
> Array of user IDs (numbers) to filter by creator. Applies to ITEMS (filters by item creator), UPDATES (filters by update author), and DASHBOARDS (filters by dashboard creator). Only pass it if the user explicitly asked to filter by specific creators. Example: \[12345, 67890].
>
> **searchTerm** `string`
>
> The search phrase — the text the search matches results against (e.g. a board name, item title, or keywords). Required and must be non-empty. This is NOT a filter or an id — pass the words to look for.
>
> **searchType** `string ("BOARD" | "DOCUMENTS" | "FOLDERS" | "WORKSPACES" | "UPDATES" | "ITEMS" | "TIMELINE_ITEMS" | "DASHBOARDS")` *required*
>
> The type of search to perform. Valid values: BOARD, DOCUMENTS, FOLDERS, WORKSPACES, UPDATES, ITEMS, TIMELINE\_ITEMS, DASHBOARDS.
>
> **workspaceIds** `array`
>
> Array of workspace IDs (numbers) to search in. Optional for FOLDERS search (searches all accessible workspaces when omitted). For ITEMS, BOARD, DOCUMENTS, DASHBOARDS, UPDATES, and TIMELINE\_ITEMS search, only pass this if the user explicitly asked to search within specific workspaces. Example: \[12345, 67890].

> [accordion] Search meetings content
>
> **Slug:** `MONDAY_MCP_SEARCH_MEETINGS_CONTENT`
>
> Search inside meeting content (topics, summary, action items) and return matching passages with their source area. Keyword-ranked (not semantic). When query is omitted, returns content filtered by date/access. Use to find where something was said or decided ("which meeting mentioned the budget freeze", "find the auth migration discussion"). Pass returned ids to get\_meetings\_content for full context.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of meetings to return (1-15). Content search is heavier, so keep this small.
>
> **query** `string`
>
> The phrase or subject to find inside meeting content. Omit or leave empty to browse content by date/access. Pass the core subject or entity, roughly 1-4 words (e.g. "pricing roadmap" or "acme renewal"), not the full question. Drop instruction words, filler, and synonyms, which dilute the ranking.
>
> **access** `string ("OWN" | "SHARED_WITH_ME" | "SHARED_WITH_ACCOUNT" | "ALL")`
>
> Filter by access level. OWN: meetings the user participated in or invited the bot to. SHARED\_WITH\_ME: shared with the user or their team. SHARED\_WITH\_ACCOUNT: shared with the entire account. ALL: all accessible meetings. Default: OWN.
>
> **search\_in** `array`
>
> Which areas of meeting content to search. TOPIC: discussed topics/talking points. SUMMARY: the AI summary. ACTION\_ITEM: action items. Defaults to \[TOPIC, SUMMARY].
>
> **start\_time\_to** `string`
>
> Only include meetings that started at or before this UTC ISO 8601 timestamp (e.g. 2026-07-28T23:59:59Z).
>
> **start\_time\_from** `string`
>
> Only include meetings that started at or after this UTC ISO 8601 timestamp (e.g. 2026-07-28T00:00:00Z).

> [accordion] Show assign
>
> **Slug:** `MONDAY_MCP_SHOW_ASSIGN`
>
> Use for requests to see or use an interactive assignment interface. \[UI COMPONENT] Renders an interactive smart assignment interface visualization that the user can see and interact with. IMPORTANT: This is a UI DISPLAY tool - use it to RENDER visual components for the user to see and interact with. Do NOT use data-fetching tools when the user explicitly asks to "show", "display", "visualize", or "see" something visually. Helps assign tasks to the right people. Assignment suggestions are based on task details (like name) and person details (such as title, availability, etc). Always show as much as data possible, while showing the person details like title etc. If you do not have the data available - use the list\_users\_and\_teams tool.
>
> #### Input Parameters
>
> **title** `string` *required*
>
> Board title
>
> **assignments** `array` *required*
>
> Array of item assignments

> [accordion] Show battery
>
> **Slug:** `MONDAY_MCP_SHOW_BATTERY`
>
> Use when user asks for: battery view, progress indicator, status distribution bar, completion percentage visualization, or Monday.com style status breakdown. \[UI COMPONENT] Renders an interactive battery/progress indicator visualization that the user can see and interact with. IMPORTANT: This is a UI DISPLAY tool - use it to RENDER visual components for the user to see and interact with. Do NOT use data-fetching tools when the user explicitly asks to "show", "display", "visualize", or "see" something visually.
>
> #### Input Parameters
>
> **data** `array` *required*
>
> Array of segments. Each segment must have 'name' (label), 'y' (value), and 'color' properties.

> [accordion] Show chart
>
> **Slug:** `MONDAY_MCP_SHOW_CHART`
>
> Use when user asks for: pie chart, bar chart, line graph, data visualization, or any graphical representation of numbers/statistics. \[UI COMPONENT] Renders an interactive chart/graph visualization that the user can see and interact with. IMPORTANT: This is a UI DISPLAY tool - use it to RENDER visual components for the user to see and interact with. Do NOT use data-fetching tools when the user explicitly asks to "show", "display", "visualize", or "see" something visually.
>
> #### Input Parameters
>
> **data** `array` *required*
>
> Array of data points. Each point must have 'name' (label) and 'y' (value) properties, with optional 'color' property.
>
> **type** `string ("pie" | "bar")` *required*
>
> Chart type to render: "pie" (circular chart with segments) or "bar" (horizontal bars).
>
> **title** `string`
>
> Optional title text to display above the chart. Leave empty or omit for no title.

> [accordion] Show table
>
> **Slug:** `MONDAY_MCP_SHOW_TABLE`
>
> Use when user asks to: display a board as table, show items in table format, view data in tabular layout, or see a Monday.com board visually. \[UI COMPONENT] Renders an interactive table visualization that the user can see and interact with. IMPORTANT: This is a UI DISPLAY tool - use it to RENDER visual components for the user to see and interact with. Do NOT use data-fetching tools when the user explicitly asks to "show", "display", "visualize", or "see" something visually. When asked to update an item, use the currently selected item ID (get it from the widget state, using tools like "get\_widget\_state") for deciding which item to update. If no item is selected, ask the user which item should be updated. After adding an update to an item, you MUST display the table AGAIN, even if the user did not ask you to.
>
> \[IMPORTANT]\[FILTERING PRECONDITION]: IF using filters, you MUST call get\_board\_info(boardId) FIRST and use the returned boardContextToken.
>
> #### Input Parameters
>
> **boardId** `string` *required*
>
> The ID of the board to display
>
> **filters** `array`
>
> The configuration of filters to apply on the items. Before sending the filters, use get\_board\_info tool to check "filteringGuidelines" key for filtering by the column.
>
> **filtersOperator** `string ("and" | "or")`
>
> The operator to use for the filters
>
> **currentlySelectedItemIdForShowingUpdates** `string`
>
> The ID of the item currently displaying its updates in the expanded view

> [accordion] Stop workflow run once
>
> **Slug:** `MONDAY_MCP_STOP_WORKFLOW_RUN_ONCE`
>
> Stops the run that run\_workflow\_once started, so the remaining steps do not execute.
>
> Use this tool only when the user asks to stop, cancel or abort the run.
>
> Stopping is best-effort: steps that already executed keep their effects — they are not undone. Say so rather than implying the run was reverted.
>
> The response is a JSON object:
>
> * status "ok": "stopped" tells you whether a run was actually stopped. When it is false there was nothing left to stop (the run already finished or never started), and "reason" may explain further.
> * status "failed": "message" explains why the stop request could not be made. Relay it.
>
> #### Input Parameters
>
> **workflowDraftId** `integer`
>
> The identifier of a draft that belongs to the workflow object referenced by workflowObjectId. When omitted, it refers to the live version of the workflow.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] Submit bug or feature request
>
> **Slug:** `MONDAY_MCP_SUBMIT_BUG_OR_FEATURE_REQUEST`
>
> Report a bug, submit a feature request, or share feedback about the monday.com product or this integration.
>
> Call this tool proactively — not just when a user explicitly asks. Use it whenever any of these signals show up: • A tool produced unexpected errors, empty results, or needed a workaround • The user tried something monday.com couldn't support and had to settle for a partial or manual solution • A recurring capability gap is noticed — something requested that simply isn't available in monday.com or this integration • The user shows repeated frustration (multiple corrections, retrying the same request, "that's wrong again," "why isn't this working") • A task required multiple retries, an unusually long reasoning chain, or many attempts for something that should've been simple
>
> Parameters: • title (string, required) — short summary, no PII • description (string, required) — full details of what happened/expected/requested, no PII • kind (enum, required) — "bug", "feature\_request", or "feedback" • tool\_name (string, optional) — the specific monday.com tool the feedback relates to (e.g. "create\_item")
>
> Restriction: Use strictly for things related to monday.com — not for other tools (Google Drive, Slack, GitHub, etc.) that may be in the conversation context. Do NOT include any personally identifiable information (PII) such as names, email addresses, phone numbers, or any other personal data.
>
> #### Input Parameters
>
> **kind** `string ("feedback" | "feature_request" | "bug")` *required*
>
> The kind of submission: general feedback, a feature request, or a bug report
>
> **title** `string` *required*
>
> A short summary of the feedback. Do NOT include any personally identifiable information (PII) such as names, email addresses, phone numbers, or any other personal data.
>
> **tool\_name** `string`
>
> The name of the monday.com MCP tool this feedback is about, if applicable (e.g. "create\_item", "get\_board\_info"). Only include monday.com MCP tool names — do not reference tools from other connected services.
>
> **description** `string` *required*
>
> Full details — what happened, what was expected, or what is being requested. Do NOT include any personally identifiable information (PII) such as names, email addresses, phone numbers, or any other personal data.

> [accordion] Update action
>
> **Slug:** `MONDAY_MCP_UPDATE_ACTION`
>
> Update an existing action. Only pass the fields you want to change.
>
> Example: id: "550e8400-e29b-41d4-a716-446655440000", name: "Updated name", code: "print('new code')"
>
> #### Input Parameters
>
> **id** `string` *required*
>
> Action ID
>
> **code** `string`
>
> New source code (max 1 MB)
>
> **name** `string`
>
> New short, descriptive action name
>
> **language** `string ("javascript" | "typescript" | "python")`
>
> New programming language — one of: javascript, typescript, python
>
> **description** `string`
>
> New description — short summary: what data the code accesses (specific boards/items by name or ID, or scope if broad), what processing it performs, and how the result is returned. Max 255 characters.
>
> **vars\_schema** `array`
>
> New variable definitions
>
> **output\_description** `string`
>
> New instructions describing what should be done with the execution output, max 2000 characters.

> [accordion] Update column
>
> **Slug:** `MONDAY_MCP_UPDATE_COLUMN`
>
> Update properties of an existing monday.com column (title, description, settings). \[REQUIRED PRECONDITION]: Uses optimistic concurrency control via the revision field — fetch the column id, type, and current revision via get\_board\_schema first (preferred), or get\_board\_info if you already have it, then call this tool. If the update fails because the revision is stale, re-fetch and try again. After a successful update, use the new revision returned in the response for any further update to this column, not the one you started with. \[REQUIRED PRECONDITION]: If you are changing columnSettings, also call get\_column\_type\_info with fetchMode "schema" for that column type first to learn the valid settings structure. columnSettings is the flat payload for that column type (e.g. \{"labels": \[...]}) — not get\_board\_info's column.settings object copied as-is, and not wrapped again as \{"settings": \{"labels": \[...]}}. To edit existing status or dropdown labels (rename, recolor, or reorder): first call get\_board\_info with filters.columns.ids for that column (or filters.columns.only) to read its current settings.labels, where each existing label's id lives. Editing an existing label requires sending its id in that label's entry — omitting it fails validation, since only a brand-new label can omit id. Status labels need the full label shape (id, label, color, index, and so on), not just a renamed string. Never invent an id — reuse the ids from get\_board\_info and add new labels without one. Flow: get\_board\_info for the revision and current settings.labels with ids, get\_column\_type\_info (schema mode) for the valid shape, then build columnSettings.labels reusing existing ids and adding new labels without id.
>
> #### Input Parameters
>
> **boardId** `number` *required*
>
> The id of the board containing the column
>
> **columnId** `string` *required*
>
> The id of the column to update
>
> **revision** `string` *required*
>
> The current revision of the column. Get it from get\_board\_schema (preferred) or get\_board\_info. Used for optimistic concurrency control — if the column changed since you read it, the request fails and you must re-fetch the latest revision before retrying. After a successful update\_column, use the new revision from the response for any further update to this column, not the one you started with.
>
> **columnType** `string ("auto_number" | "board_relation" | "button" | "checkbox" | "color_picker" | "country" | "creation_log" | "date" | "dependency" | "direct_doc" | "doc" | "dropdown" | "email" | "file" | "formula" | "group" | "hour" | "integration" | "item_assignees" | "item_id" | "last_updated" | "link" | "location" | "long_text" | "mirror" | "name" | "numbers" | "people" | "phone" | "progress" | "rating" | "status" | "subtasks" | "tags" | "team" | "text" | "time_tracking" | "timeline" | "unsupported" | "vote" | "week" | "world_clock")` *required*
>
> The type of the column being updated. Must match the existing column type.
>
> **columnTitle** `string`
>
> The new title of the column. If omitted, the title is unchanged.
>
> **columnSettings** `string`
>
> Type-specific configuration as a JSON string. If omitted, settings are unchanged. Shape depends on columnType — see tool description for how to obtain it.
>
> **columnDescription** `string`
>
> The new description of the column. If omitted, the description is unchanged.

> [accordion] Update doc
>
> **Slug:** `MONDAY_MCP_UPDATE_DOC`
>
> Update an existing monday.com document. Provide doc\_id (preferred) or object\_id, plus an ordered operations array (executed sequentially, stops on first failure).
>
> OPERATIONS:
>
> * set\_name: Rename the document.
> * add\_markdown\_content: Append markdown as blocks (or insert after a block). Best for text, headings, lists, simple tables — no block IDs needed.
> * update\_block: Update content of an existing text, code, or list\_item block in-place.
> * create\_block: Create a new block at a precise position. Use parent\_block\_id to nest inside notice\_box, table cell, or layout cell.
> * delete\_blocks: Permanently delete 1–100 blocks in one call. Provide all block IDs in the block\_ids array. The ONLY option for BOARD, WIDGET, DOC embed, and GIPHY blocks.
> * replace\_block: Delete a block and create a new one in its place (use when update\_block is not supported).
> * add\_comment: Create a new comment or reply on the document (doc-level, block-level, or text-selection).
>
> WHEN TO USE EACH OPERATION:
>
> * text / code / list\_item → update\_block. Use replace\_block to change subtype (e.g. NORMAL\_TEXT→LARGE\_TITLE)
> * divider / table / image / video / notice\_box / layout → replace\_block (properties immutable after creation)
> * BOARD / WIDGET / DOC / GIPHY → delete\_blocks only
>
> GETTING BLOCK IDs: Call read\_docs with include\_blocks: true — returns id, type, position, and content per block.
>
> BLOCK CONTENT (delta\_format): Array of insert ops. Last op MUST be \{insert: \{text: "\n"}}.
>
> * Plain: \[\{insert: \{text: "Hello"}}, \{insert: \{text: "\n"}}]
> * Bold: \[\{insert: \{text: "Hi"}, attributes: \{bold: true}}, \{insert: \{text: "\n"}}]
> * Mention user/doc/board: \[\{insert: \{text: "Hey "}}, \{insert: \{mention: \{id: 12345, type: "USER"}}}, \{insert: \{text: "\n"}}] — type is USER, DOC, or BOARD. id is numeric (user IDs from list\_users\_and\_teams)
> * Inline column value: \[\{insert: \{column\_value: \{item\_id: 111, column\_id: "status"}}}, \{insert: \{text: "\n"}}]
> * Supported attributes: bold, italic, underline, strike, code, link, color, background (not applicable to mention/column\_value ops)
>
> IMAGE WITH ASSET: For asset-based images, use create\_block with block\_type "image" and asset\_id (instead of public\_url). add\_markdown\_content does NOT support asset images — for mixed content, alternate add\_markdown\_content (text) and create\_block (image) operations in sequence.
>
> BATCHING DELETES: delete\_blocks accepts 1..100 IDs. Put ALL IDs in one operation's block\_ids array. Never emit multiple delete\_blocks operations in a row.
>
> COMMENTS:
>
> * add\_comment: Create a new comment or reply on the document. Three scopes:
>   * Doc-level (no block\_id): comment appears on the doc as a whole.
>   * Block-level (block\_id only): comment is anchored to a specific block. The block shows a comment indicator in the UI.
>   * Text-selection (block\_id + selection\_from + selection\_length): comment is anchored to a specific character range inside a text/code/list\_item block. That text is highlighted with a comment marker. Block-level and text-selection comments only work on blocks with text content (text, code, list\_item, title, quote). They do NOT work on: divider, page\_break, table, layout, notice\_box, image, video, or giphy blocks. Get block IDs from read\_docs with include\_blocks: true. Format body with HTML, not markdown. Use mentions\_list for @mentions.
>
> #### Input Parameters
>
> **doc\_id** `string`
>
> The document ID (the id field from read\_docs). Takes priority over object\_id if both are provided.
>
> **object\_id** `string`
>
> The document object ID (the object\_id field from read\_docs, visible in the document URL). Resolved to doc\_id.
>
> **operations** `array` *required*
>
> Ordered list of operations to perform. Executed sequentially. Stops at first failure.  Operation types: - set\_name: Rename the document. - add\_markdown\_content: Append markdown as blocks (simplest for text/lists/tables). - update\_block: Change content of an existing text/code/list/divider block. - create\_block: Create a new block at a specific position (supports text, list\_item, code, divider, page\_break, image, video, notice\_box, table, layout). - delete\_blocks: Permanently delete 1–100 blocks in one call. Provide all block IDs in the block\_ids array. Works for all block types including BOARD, WIDGET, DOC embed, and GIPHY. - replace\_block: Delete a block and create a new one in its place. Use for: changing image/video source, table restructure, notice\_box theme change. - add\_comment: Create a new comment or reply on the document. Use parent\_update\_id to reply to an existing comment. Format text with HTML. Uses the doc's backing board item.  WHEN TO USE WHICH: - Adding new text sections → add\_markdown\_content - Adding asset-based images → create\_block with block\_type "image" and asset\_id (add\_markdown\_content does NOT support asset images) - Mixed content with asset images → alternate add\_markdown\_content (for text) and create\_block (for each image) in sequence - Editing existing text block → update\_block - Changing an image URL → replace\_block (image URL is immutable after creation) - Changing video URL → replace\_block - Restructuring a table → replace\_block - BOARD/WIDGET/DOC/GIPHY blocks → delete\_blocks only (no public API to create these)  NESTING CONTENT IN CONTAINERS: - notice\_box: Fully supported. Create the notice\_box first, then in a separate call create child blocks with parent\_block\_id set to the notice\_box ID. You cannot reference a block ID created in the same call. - table: Cell-level API nesting is NOT supported. To create a table with content, use add\_markdown\_content with a markdown table (e.g. "| H1 | H2 |\n| --- | --- |\n| A | B |"). This creates a pre-populated table in one shot. Empty tables created via create\_block cannot have their cells populated through the API. - layout: Cell-level API nesting is NOT supported and there is no markdown equivalent. Layouts can only be created empty via create\_block. No workaround exists to populate layout columns through the API. Deleting a container does NOT delete its children — delete children first for clean removal.  BATCHING: delete\_blocks accepts 1..100 IDs. Put ALL IDs in one operation's block\_ids array. Never emit multiple delete\_blocks operations in a row.  Block IDs are available in the blocks array returned by read\_docs.

> [accordion] Update folder
>
> **Slug:** `MONDAY_MCP_UPDATE_FOLDER`
>
> Update an existing folder in monday.com
>
> #### Input Parameters
>
> **name** `string`
>
> The new name of the folder
>
> **color** `string ("AQUAMARINE" | "BRIGHT_BLUE" | "BRIGHT_GREEN" | "CHILI_BLUE" | "DARK_ORANGE" | "DARK_PURPLE" | "DARK_RED" | "DONE_GREEN" | "INDIGO" | "LIPSTICK" | "NULL" | "PURPLE" | "SOFIA_PINK" | "STUCK_RED" | "SUNSET" | "WORKING_ORANGE")`
>
> The new color of the folder
>
> **folderId** `string` *required*
>
> The ID of the folder to update
>
> **customIcon** `string ("FOLDER" | "MOREBELOW" | "MOREBELOWFILLED" | "NULL" | "WORK")`
>
> The new custom icon of the folder
>
> **fontWeight** `string ("FONT_WEIGHT_BOLD" | "FONT_WEIGHT_LIGHT" | "FONT_WEIGHT_NORMAL" | "FONT_WEIGHT_VERY_LIGHT" | "NULL")`
>
> The new font weight of the folder
>
> **workspaceId** `string`
>
> The ID of the workspace containing the folder
>
> **parentFolderId** `string`
>
> The ID of the new parent folder
>
> **accountProductId** `string`
>
> The account product ID associated with the folder
>
> **position\_is\_after** `boolean`
>
> Whether to position the folder after the object
>
> **position\_object\_id** `string`
>
> The ID of the object to position the folder relative to. If this parameter is provided, position\_object\_type must be also provided.
>
> **position\_object\_type** `string ("Board" | "Folder" | "Overview")`
>
> The type of object to position the folder relative to. If this parameter is provided, position\_object\_id must be also provided.

> [accordion] Update form
>
> **Slug:** `MONDAY_MCP_UPDATE_FORM`
>
> Update a monday.com form. Use the action field to specify the operation. \[REQUIRED PRECONDITION]: Call get\_form first to read the current form state — you need it to resolve the formToken, and for actions that reference existing entities (updateQuestionOrder needs the question ids, deleteTag needs the tag id) or that overwrite existing settings (updateAppearance, updateAccessibility, updateFeatures, updateFormHeader).
>
> #### Input Parameters
>
> **tag** `object`
>
> Tag to create/delete. Delete: id only. Create: name (id/columnId auto-generated).
>
> **form** `object`
>
> Form data to update (patch semantics).
>
> **action** `string ("activate" | "deactivate" | "shortenFormUrl" | "setFormPassword" | "createTag" | "deleteTag" | "updateAppearance" | "updateAccessibility" | "updateFeatures" | "updateQuestionOrder" | "updateFormHeader")` *required*
>
> Action to execute on the form. Each action requires different fields — check field descriptions to know what to include.
>
> **formToken** `string` *required*
>
> **formPassword** `string`
>
> Required for setFormPassword action.

> [accordion] Update items
>
> **Slug:** `MONDAY_MCP_UPDATE_ITEMS`
>
> Update column values for up to 40 items in a single call. Each update targets one item by itemId and sets one or more column values on it. Each update is independent - it can target its own board via boardId and set its own column values, so a single call can update many items across multiple boards, apply the same value to many items, or apply different values per item. Each update returns its own item\_id and item\_url on success or a raw error message on failure. To link board-relation columns, call link\_board\_items\_workflow before using this tool. \[REQUIRED PRECONDITION]: Before using this tool, if you are not familiar with the board structure (column IDs, column types, status labels), first use get\_board\_info with filters.columns.only to get column metadata without fetching views. This is essential for constructing valid column values.
>
> #### Input Parameters
>
> **boardId** `number`
>
> Optional default board id used for any update that does not set its own boardId. Each update can override it with its own boardId, so a single call can span multiple boards.
>
> **updates** `array` *required*
>
> The item updates to apply, up to 40 per call. Each entry updates one item and returns its own result on success or a raw error message on failure. Each entry independently chooses its boardId, columnValues, and createLabelsIfMissing.

> [accordion] Update view
>
> **Slug:** `MONDAY_MCP_UPDATE_VIEW`
>
> Update an existing board view (tab) — change its name, filter rules, or sort order. Provide only the fields you want to change.
>
> Filter operators: any\_of, not\_any\_of, is\_empty, is\_not\_empty, greater\_than, lower\_than, between, contains\_text, not\_contains\_text
>
> #### Input Parameters
>
> **name** `string`
>
> New name for the view (omit to leave unchanged)
>
> **sort** `array`
>
> Sort configuration for the view
>
> **tags** `array`
>
> Tags to apply to the view
>
> **type** `string ("TABLE" | "DASHBOARD" | "FORM" | "APP")` *required*
>
> The type of the board view being updated
>
> **filter** `object`
>
> Filter configuration for the view
>
> **viewId** `string` *required*
>
> The ID of the view to update
>
> **boardId** `string` *required*
>
> The board ID the view belongs to
>
> **settings** `string`
>
> Type-specific view settings as a JSON object

> [accordion] Update view table
>
> **Slug:** `MONDAY_MCP_UPDATE_VIEW_TABLE`
>
> Update an existing table-type board view — change its name, filters, sort, tags, or table-specific settings including conditional coloring (highlight rows/cells based on column values). Provide only the fields you want to change.
>
> CONDITIONAL COLORING: Use settings.conditional\_coloring to highlight rows or cells. Each rule specifies a column\_id, operator, value (human-readable — e.g. "Stuck", not an index), color, and entire\_row flag. Example: highlight rows where Status is "Stuck" in red, or where Salary > 100000 in green.
>
> Filter operators: any\_of, not\_any\_of, is\_empty, is\_not\_empty, greater\_than, lower\_than, between, contains\_text, not\_contains\_text
>
> #### Input Parameters
>
> **name** `string`
>
> New name for the view (omit to leave unchanged)
>
> **sort** `array`
>
> Sort configuration for the view
>
> **tags** `array`
>
> Tags to apply to the view
>
> **filter** `object`
>
> Filter configuration for the view
>
> **viewId** `string` *required*
>
> The ID of the table view to update
>
> **boardId** `string` *required*
>
> The board ID the view belongs to
>
> **settings** `object`
>
> Table-specific settings (column visibility/order, group-by)

> [accordion] Update workspace
>
> **Slug:** `MONDAY_MCP_UPDATE_WORKSPACE`
>
> Update an existing workspace in monday.com
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The ID of the workspace to update
>
> **attributeKind** `string ("closed" | "open" | "template")`
>
> The kind of the workspace to update (open / closed / template)
>
> **attributeName** `string`
>
> The name of the workspace to update
>
> **attributeDescription** `string`
>
> The description of the workspace to update
>
> **attributeAccountProductId** `number`
>
> The target account product's ID to move the workspace to

> [accordion] Validate workflow
>
> **Slug:** `MONDAY_MCP_VALIDATE_WORKFLOW`
>
> Validates the current workflow's structure and step configuration. Reports issues such as a missing trigger or action block, a delay/wait-trigger block left as a leaf, an empty loop, unknown blocks, missing required inputs, type mismatches between a variable and the field it's bound to, cross-branch node-results references, or invalid variable values.
>
> Use this tool when:
>
> * The user asks "is my workflow ready?", "what's missing?", "can I publish?", "validate my workflow", or similar.
> * After you finished structural changes, to confirm the user still has things to configure.
> * Before suggesting the user publish/activate the workflow.
>
> The tool does NOT modify the workflow. It only inspects the current state. The response is always a JSON object with an "issues" array; an empty array means the workflow is fully configured. Each issue has a "code" discriminator with code-specific fields, and (when applicable) is enriched with stepVisibleId, stepTitle, and blockName for human-readable context.
>
> #### Input Parameters
>
> **workflowDraftId** `integer`
>
> The identifier of a draft that belongs to the workflow object referenced by workflowObjectId. When omitted, it refers to the live version of the workflow.
>
> **workflowObjectId** `number` *required*
>
> The identifier of a workflow object, found in the workflow URL or returned by create\_workflow. A workflow object is the entity that is retained across published versions; users can create draft versions related to this workflow object. This is NOT an automation id: the workflowId returned by create\_automation identifies a board automation, which these tools cannot address.

> [accordion] Vibe ask
>
> **Slug:** `MONDAY_MCP_VIBE_ASK`
>
> Ask a read-only question about an existing Vibe app. Blocks for up to 45s (configurable via timeout\_ms) awaiting the assistant reply. Status: COMPLETED with the reply, TIMEOUT if the workflow did not finish in time (call vibe\_get later to retrieve it), or FAILED if the workflow errored or was cancelled. Optional model to pick the LLM for the answer.
>
> #### Input Parameters
>
> **model** `string ("GEMINI_3_5_FLASH" | "CLAUDE_4_5_SONNET" | "CLAUDE_OPUS_4_6" | "GEMINI_3_7_FLASH" | "CLAUDE_5_SONNET" | "CLAUDE_OPUS_5")`
>
> LLM model for code generation. Omit for automatic selection. Requires model selection enabled for the account.
>
> **app\_id** `integer` *required*
>
> Internal Vibe app id
>
> **prompt** `string` *required*
>
> Question to ask about the app — read-only, no code changes
>
> **timeout\_ms** `integer`
>
> Maximum time to block waiting for the assistant reply (default 45s)

> [accordion] Vibe create
>
> **Slug:** `MONDAY_MCP_VIBE_CREATE`
>
> Creates a new Vibe app from a natural-language prompt. Returns immediately with app\_id and editor\_link — the URL of the Vibe builder/chat page for the new app (https\://\{accountSlug}.monday.com/vibe/app/\{appId}); the user can open it right away to watch generation in progress. Generation itself runs asynchronously — poll vibe\_get for status. Optional: workspace\_id to create the app in a specific workspace, board\_ids to connect existing boards (omit to auto-create), view\_id to host a dashboard widget, and model to pick the LLM.
>
> #### Input Parameters
>
> **model** `string ("GEMINI_3_5_FLASH" | "CLAUDE_4_5_SONNET" | "CLAUDE_OPUS_4_6" | "GEMINI_3_7_FLASH" | "CLAUDE_5_SONNET" | "CLAUDE_OPUS_5")`
>
> LLM model for code generation. Omit for automatic selection. Requires model selection enabled for the account.
>
> **prompt** `string` *required*
>
> Natural-language description of the app to build
>
> **variant** `string ("board_view" | "item_view" | "vibe_item_view" | "object" | "vibe_dashboard_widget" | "object_fullstack" | "monday_campaigns")`
>
> App variant.
>
> **view\_id** `string`
>
> Board view ID that hosts the widget — required for vibe\_dashboard\_widget (the widget is created on this board view), and must be accompanied by its board\_id.
>
> **board\_ids** `array`
>
> Existing board IDs to connect (they must exist and you must have edit access). For multi-board variants (object, object\_fullstack) these are connected as data sources; the number allowed depends on your account tier. For single-board variants (board\_view, vibe\_dashboard\_widget, item views) provide one board id, used as the host board. Omit to have a new board created automatically.
>
> **workspace\_id** `string`
>
> Workspace ID to create the app in (you must have create permissions on it). Omit to use the default Vibe workspace. Board-hosted variants (board\_view, vibe\_item\_view, vibe\_dashboard\_widget) live on their host board — there this only sets where auto-created boards go.

> [accordion] Vibe delete
>
> **Slug:** `MONDAY_MCP_VIBE_DELETE`
>
> Delete a Vibe app and its associated assets. Destructive.
>
> #### Input Parameters
>
> **app\_id** `integer` *required*
>
> Internal Vibe app id

> [accordion] Vibe get
>
> **Slug:** `MONDAY_MCP_VIBE_GET`
>
> Fetch a Vibe app by id. App metadata is always returned, including editor\_link — the URL of the Vibe builder/chat page for this app (https\://\{accountSlug}.monday.com/vibe/app/\{appId}); usable as soon as the app row exists. Pass `include` to add expensive slices: status (refreshes status + adds is\_busy, default true), messages (with optional from\_date), code\_versions.
>
> #### Input Parameters
>
> **app\_id** `integer` *required*
>
> Internal Vibe app id
>
> **include** `object`
>
> Conditional fetch — app metadata is always returned; flags add expensive slices

> [accordion] Vibe list
>
> **Slug:** `MONDAY_MCP_VIBE_LIST`
>
> List Vibe apps owned by the authenticated user. Supports pagination, search, status, and is\_published filters.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number (1-indexed)
>
> **limit** `integer`
>
> Maximum number of apps to return
>
> **status** `string ("created" | "generating" | "processing_message" | "deploying" | "ready")`
>
> Filter by app status
>
> **search\_term** `string`
>
> Filter by name (case-insensitive substring match)
>
> **is\_published** `boolean`
>
> Filter by publish state

> [accordion] Vibe publication
>
> **Slug:** `MONDAY_MCP_VIBE_PUBLICATION`
>
> Manage the publication state of a Vibe app on the caller account. action=publish requires the app to be deployed and respects the published-apps license limit. action=unpublish removes the app from the account.
>
> #### Input Parameters
>
> **action** `string ("publish" | "unpublish")` *required*
>
> publish = make the app live on the caller account; unpublish = remove it from the account
>
> **app\_id** `integer` *required*
>
> Internal Vibe app id

> [accordion] Vibe update
>
> **Slug:** `MONDAY_MCP_VIBE_UPDATE`
>
> Sends a follow-up message to modify an existing app. Fire-and-forget — returns immediately with user\_message\_id and editor\_link (the Vibe builder/chat URL for this app, https\://\{accountSlug}.monday.com/vibe/app/\{appId}). Returns APP\_BUSY (409) if the app is currently generating; poll vibe\_get first. Optional model to pick the LLM for this build.
>
> #### Input Parameters
>
> **model** `string ("GEMINI_3_5_FLASH" | "CLAUDE_4_5_SONNET" | "CLAUDE_OPUS_4_6" | "GEMINI_3_7_FLASH" | "CLAUDE_5_SONNET" | "CLAUDE_OPUS_5")`
>
> LLM model for code generation. Omit for automatic selection. Requires model selection enabled for the account.
>
> **app\_id** `integer` *required*
>
> Internal Vibe app id
>
> **prompt** `string` *required*
>
> Follow-up message describing what to change in the app

> [accordion] Workspace info
>
> **Slug:** `MONDAY_MCP_WORKSPACE_INFO`
>
> This tool returns the boards, docs and folders in a workspace and which folder they are in. It returns up to 100 of each object type, if you receive 100 assume there are additional objects of that type in the workspace.
>
> #### Input Parameters
>
> **workspace\_id** `number` *required*
>
> The ID of the workspace to get information for
