> ## 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.

# Customgpt

> CustomGPT.ai is a platform that enables users to create and integrate AI-powered chatbots tailored to their specific data and requirements.

![Customgpt logo](https://mintcdn.com/composio-preview/VNLruGH5mLZqXdPH/images/toolkits/customgpt.svg?fit=max\&auto=format\&n=VNLruGH5mLZqXdPH\&q=85\&s=8672d9d7879b8c29a426513274ef2534)

* **Category:** ai chatbots
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 40
* **Triggers:** 0
* **Slug:** `CUSTOMGPT`
* **Version:** 20261101\_00

## Tools

> [accordion] Activate Persona Version
>
> **Slug:** `CUSTOMGPT_ACTIVATE_PERSONA_VERSION`
>
> Restore a previous persona version for a CustomGPT agent. Activates a previous persona version, making it the current active persona. This creates a new version entry in the history (it doesn't overwrite), preserving the full audit trail. Use this to roll back to a known-good configuration. Requires Custom plan.
>
> #### Input Parameters
>
> **version** `integer` *required*
>
> The version number of the persona to activate. This must be a valid version from the persona history.
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent (formerly known as project). Obtain this from the List Projects action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Add Source to Project
>
> **Slug:** `CUSTOMGPT_ADD_SOURCE`
>
> Add a data source to a CustomGPT agent's knowledge base using a sitemap URL or file upload. Use this to add documentation, FAQs, or other knowledge content to an agent.
>
> #### Input Parameters
>
> **file** `object`
>
> File to upload as a source (PDF, DOC, TXT, etc.). Required if sitemap\_path is not provided.
>
> **project\_id** `integer` *required*
>
> The unique identifier of the agent (formerly known as project) to add the source to.
>
> **sitemap\_path** `string`
>
> URL of the sitemap to use as a source (e.g., '[https://docs.example.com/sitemap.xml](https://docs.example.com/sitemap.xml)'). Required if file is not provided.
>
> **is\_anonymized** `boolean`
>
> Whether to anonymize the data in the source.
>
> **is\_ocr\_enabled** `boolean`
>
> Whether to enable OCR (Optical Character Recognition) for extracting text from images in the file.
>
> **is\_vision\_enabled** `boolean`
>
> Whether to enable vision processing for images in the file source. Allows the agent to analyze and understand image content.
>
> **file\_data\_retension** `boolean`
>
> Whether to retain file data after processing.
>
> **image\_extraction\_type** `string ("none" | "sync_from_sitemap")`
>
> Type of image extraction from website.
>
> **is\_vision\_compress\_image** `boolean`
>
> Whether to compress images for vision processing. Reduces storage and improves performance.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Clone CustomGPT Project
>
> **Slug:** `CUSTOMGPT_CLONE_PROJECT`
>
> Tool to clone a CustomGPT agent (project). Creates a complete copy of an existing agent, including its knowledge base, persona, and settings. Use this to create variations of an agent for testing, or to use an existing agent as a template for a new one.
>
> #### Input Parameters
>
> **projectId** `integer` *required*
>
> The unique agent identifier of the project to clone
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Conversation
>
> **Slug:** `CUSTOMGPT_CREATE_CONVERSATION`
>
> Tool to create a new conversation session for a CustomGPT agent. Use this when starting a new chat interaction - it returns a session ID that you'll use to send messages. Optionally provide a name to help identify the conversation later.
>
> #### Input Parameters
>
> **name** `string`
>
> Optional name to identify the conversation. Helps organize and reference conversations later. If not provided, a default name will be assigned.
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent (formerly known as project). Obtain this from the List Projects action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create CustomGPT Project
>
> **Slug:** `CUSTOMGPT_CREATE_PROJECT`
>
> Create a new CustomGPT agent from either a sitemap URL or a file upload. Exactly one source must be provided; the agent processes the content to build its knowledge base.
>
> #### Input Parameters
>
> **file** `object`
>
> File to upload for the agent's knowledge base. Either file or sitemap\_path must be provided, not both.
>
> **project\_name** `string` *required*
>
> Name for the new agent. This will be the display name of the agent.
>
> **sitemap\_path** `string`
>
> URL of sitemap to import content from. The agent will crawl and index content from this sitemap. Either sitemap\_path or file must be provided, not both.
>
> **is\_anonymized** `boolean`
>
> Whether to anonymize data in the agent's knowledge base. Use this to protect sensitive information.
>
> **is\_ocr\_enabled** `boolean`
>
> Whether to enable OCR (Optical Character Recognition) for extracting text from images and scanned documents.
>
> **is\_vision\_enabled** `boolean`
>
> Whether to enable vision processing for images in the file source. Allows the agent to process and understand images.
>
> **file\_data\_retension** `boolean`
>
> Whether to retain file data after processing. If false, only extracted text is kept.
>
> **is\_vision\_compress\_image** `boolean`
>
> Whether to compress images for vision processing. Reduces storage and processing costs for image-heavy content.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Page from Agent
>
> **Slug:** `CUSTOMGPT_DELETE_PAGE`
>
> Tool to delete a document from a CustomGPT agent's knowledge base. Permanently removes a document and the agent will no longer reference this content when answering questions. Use this to remove outdated or incorrect information. Warning: This action cannot be undone.
>
> #### Input Parameters
>
> **pageId** `integer` *required*
>
> The page id
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete CustomGPT Project
>
> **Slug:** `CUSTOMGPT_DELETE_PROJECT`
>
> Tool to delete a CustomGPT project by ID. Use when you need to permanently remove an existing agent after confirming the ID.
>
> #### Input Parameters
>
> **projectId** `string` *required*
>
> Unique ID of the agent (project) to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete CustomGPT Project License
>
> **Slug:** `CUSTOMGPT_DELETE_PROJECT_LICENSE`
>
> Delete a license from a CustomGPT project or agent using its numeric project ID and license ID. The operation succeeds if the license is already absent.
>
> #### Input Parameters
>
> **licenseId** `string` *required*
>
> Unique identifier of the license to delete from the project
>
> **projectId** `string` *required*
>
> Numeric ID of the CustomGPT agent/project (as string, e.g., '90631'). The API requires integer-formatted project IDs.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete CustomGPT Source
>
> **Slug:** `CUSTOMGPT_DELETE_SOURCE`
>
> Tool to delete a data source from a CustomGPT agent. Removes the source and all its documents from the agent's knowledge base. Use this to disconnect content that's no longer relevant or to clean up after testing.
>
> #### Input Parameters
>
> **sourceId** `integer` *required*
>
> The unique identifier of a source to delete.
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Export Leads
>
> **Slug:** `CUSTOMGPT_EXPORT_LEADS`
>
> Export leads from a CustomGPT project. Returns lead information captured from conversations including email addresses, names, phone numbers, and custom fields. Supports pagination and date range filtering. Use this to sync leads with CRM or marketing tools.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number for pagination (≥1). If not specified, returns the first page.
>
> **limit** `integer`
>
> Number of items per page (1-500). Defaults to 100 if not specified.
>
> **end\_date** `string`
>
> End date for filtering leads (ISO 8601 format, e.g., '2024-12-31T23:59:59Z'). Only leads up to this date will be included.
>
> **projectId** `integer` *required*
>
> The unique ID of the project to export leads from.
>
> **start\_date** `string`
>
> Start date for filtering leads (ISO 8601 format, e.g., '2024-01-01T00:00:00Z'). Only leads from this date onwards will be included.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Message
>
> **Slug:** `CUSTOMGPT_GET_MESSAGE`
>
> Tool to get message details from a CustomGPT conversation. Returns the complete details for a single message, including the user's prompt, the agent's response, timestamps, citations, and any attached metadata.
>
> #### Input Parameters
>
> **promptId** `integer` *required*
>
> The message id of the message
>
> **projectId** `integer` *required*
>
> The ID of the agent to get the message for
>
> **sessionId** `string` *required*
>
> The session ID of the conversation to get the message from
>
> **includeInsights** `array`
>
> Fields to expand in the response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Message Trust Score
>
> **Slug:** `CUSTOMGPT_GET_MESSAGE_TRUST_SCORE`
>
> Retrieves verification trust assessment data for a message in a CustomGPT conversation. The result can include an overall status and stakeholder evaluations; trust data may be absent.
>
> #### Input Parameters
>
> **promptId** `integer` *required*
>
> The message ID of the message to get the trust score for.
>
> **projectId** `integer` *required*
>
> The ID of the agent to get the message trust score for.
>
> **sessionId** `string` *required*
>
> The session ID of the conversation containing the message.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Page Metadata
>
> **Slug:** `CUSTOMGPT_GET_PAGE_METADATA`
>
> Tool to get document metadata including title, source URL, word count, and custom metadata fields. Use this to display document information or manage your knowledge base.
>
> #### Input Parameters
>
> **pageId** `string` *required*
>
> The unique identifier of the page.
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Agent Plugins
>
> **Slug:** `CUSTOMGPT_GET_PLUGINS`
>
> Retrieves plugin details for a specific CustomGPT agent, including configuration, status, and metadata. HTTP errors may be returned in the response rather than raised.
>
> #### Input Parameters
>
> **projectId** `integer` *required*
>
> The unique agent id to retrieve plugin details for.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get CustomGPT Project
>
> **Slug:** `CUSTOMGPT_GET_PROJECT`
>
> Get details for a specific CustomGPT agent, including its status and metadata such as ownership, sharing, sitemap, and embed information.
>
> #### Input Parameters
>
> **width** `string`
>
> The width of the embed code. Defaults to 100%.
>
> **height** `string`
>
> The height of the embed code. Defaults to auto.
>
> **projectId** `integer` *required*
>
> The unique agent identifier.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project License
>
> **Slug:** `CUSTOMGPT_GET_PROJECT_LICENSE`
>
> Retrieve a license for a specific CustomGPT project by license ID. HTTP error responses may be returned as response data rather than raised as errors.
>
> #### Input Parameters
>
> **licenseId** `string` *required*
>
> Unique identifier of the license to retrieve.
>
> **projectId** `string` *required*
>
> Unique identifier of the project to which the license belongs.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Project Settings
>
> **Slug:** `CUSTOMGPT_GET_PROJECT_SETTINGS`
>
> Retrieves configuration settings for a CustomGPT agent, including avatar, background, prompt, language, and branding preferences. Error details may be returned in the response for unsuccessful requests.
>
> #### Input Parameters
>
> **projectId** `string` *required*
>
> The unique ID of the agent/project whose settings to retrieve
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Analytics Chart Data
>
> **Slug:** `CUSTOMGPT_GET_REPORT_ANALYSIS`
>
> Tool to retrieve analytics chart data for a CustomGPT project. Returns time-series data formatted for charts, with daily or weekly breakdowns of key metrics including conversation counts, query counts, and queries-per-conversation ratios. Use this to generate usage reports, track project engagement over time, or visualize chatbot performance trends.
>
> #### Input Parameters
>
> **filters** `array` *required*
>
> List of metrics to include in the response. Choose from: conversations (total conversation count), queries (total query count), or queries\_per\_conversation (average queries per conversation). You can request one or multiple metrics.
>
> **interval** `string ("daily" | "weekly")`
>
> Interval for aggregating analytics data.
>
> **project\_id** `integer` *required*
>
> The ID of the agent/project to get analytics for
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Conversation Analytics
>
> **Slug:** `CUSTOMGPT_GET_REPORT_CONVERSATIONS`
>
> Tool to get conversation analytics for a CustomGPT project. Returns conversation metrics including total conversations, average queries per conversation, and other engagement statistics. Use this to understand how users engage with your agent and analyze conversation patterns over time.
>
> #### Input Parameters
>
> **filters** `string`
>
> Filters to return conversation metrics for. Accepts a JSON array format (as a string). An empty array '\[]' is valid and returns all conversation metrics.
>
> **project\_id** `integer` *required*
>
> The ID of the agent to get conversations analytics for. Obtain this from the List Projects action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Customer Intelligence Report
>
> **Slug:** `CUSTOMGPT_GET_REPORT_INTELLIGENCE`
>
> Tool to get customer intelligence for a CustomGPT project. Returns AI-analyzed insights about users including common intents, emotional sentiment, frequently discussed topics, and emerging trends. Use this to understand what users are asking about and identify patterns in user behavior.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number for pagination (≥1). Defaults to 1 if not specified.
>
> **leads** `array`
>
> Filter results by Lead Captured status (1 for captured, 0 for not captured). Multiple values allowed.
>
> **limit** `integer`
>
> Number of items per page (1-1000). Defaults to 100 if not specified.
>
> **country** `array`
>
> Filter results by User Location (country codes or names). Multiple values allowed.
>
> **user\_id** `array`
>
> Filter results by Query Sent By (user IDs). Multiple values allowed.
>
> **accuracy** `string`
>
> Filter results by Verified Claims Score as range (format: min-max, e.g., '0-100').
>
> **end\_date** `string`
>
> End date for filtering data (ISO 8601 format recommended).
>
> **language** `array`
>
> Filter results by Query Language. Multiple values allowed.
>
> **project\_id** `integer` *required*
>
> The ID of the project to get customer intelligence for.
>
> **start\_date** `string`
>
> Start date for filtering data (ISO 8601 format recommended).
>
> **external\_id** `array`
>
> Filter results by CRM ID. Multiple values allowed.
>
> **user\_intent** `array`
>
> Filter results by User Intent (e.g., 'informational', 'transactional'). Multiple values allowed.
>
> **user\_emotion** `array`
>
> Filter results by User Emotion (e.g., 'positive', 'negative', 'neutral'). Multiple values allowed.
>
> **risk\_fidelity** `array`
>
> Filter results by Risk: Fidelity (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
>
> **content\_source** `array`
>
> Filter results by Content Source (e.g., 'in-context'). Multiple values allowed.
>
> **request\_source** `array`
>
> Filter results by Deployment source. Multiple values allowed.
>
> **risk\_jailbreak** `array`
>
> Filter results by Risk: Jailbreak (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
>
> **risk\_profanity** `array`
>
> Filter results by Risk: Profanity (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
>
> **stakeholder\_status** `array`
>
> Filter results by Stakeholder Status (e.g., 'APPROVED'). Multiple values allowed.
>
> **risk\_prompt\_leakage** `array`
>
> Filter results by Risk: Prompt Leakage (e.g., 'unavailable', 'low', 'high'). Multiple values allowed.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Traffic Analytics Report
>
> **Slug:** `CUSTOMGPT_GET_REPORT_TRAFFIC`
>
> Tool to retrieve traffic analytics for a CustomGPT agent/project. Returns user traffic metrics including unique visitors, session counts, geographic distribution, and device types. Use this to understand who's using your agent and how they're accessing it.
>
> #### Input Parameters
>
> **filters** `array`
>
> Filters to apply when retrieving traffic metrics. Pass an empty array to get all traffic data without filters.
>
> **project\_id** `integer` *required*
>
> The ID of the agent/project to get traffic analytics for.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Agent Statistics
>
> **Slug:** `CUSTOMGPT_GET_STATS`
>
> Get usage and document statistics for a CustomGPT agent, including query counts, credits used, and pages found, crawled, and indexed.
>
> #### Input Parameters
>
> **project\_id** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Usage Limits
>
> **Slug:** `CUSTOMGPT_GET_USAGE_LIMITS`
>
> Get account usage and limits for projects, storage credits, and API queries. Missing usage or limit fields are returned as zero.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Current User Profile
>
> **Slug:** `CUSTOMGPT_GET_USER_PROFILE`
>
> Tool to retrieve the current user's profile information. Use when you need to display or verify authenticated user details after login.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Conversation Messages
>
> **Slug:** `CUSTOMGPT_LIST_CONVERSATION_MESSAGES`
>
> Retrieve messages from a CustomGPT conversation, including user queries and AI responses. Returns an empty list for HTTP 204 or 404; paginated responses yield the returned page of messages.
>
> #### Input Parameters
>
> **projectId** `string` *required*
>
> The unique numeric identifier of the CustomGPT project (agent). Obtain this from the List Projects action.
>
> **sessionId** `string` *required*
>
> The unique session identifier (UUID format) of the conversation. Obtained when creating a new conversation or listing conversations.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Agent Documents
>
> **Slug:** `CUSTOMGPT_LIST_PAGES`
>
> Lists documents in a CustomGPT agent's knowledge base, including webpages and uploaded files. Returns page records and supports filtering by crawl or index status and pagination.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number to return. Defaults to 1 if not specified.
>
> **limit** `integer`
>
> Number of documents to return per page. Defaults to 20 if not specified.
>
> **order** `string ("asc" | "desc")`
>
> Order direction for sorting pages by ID.
>
> **projectId** `integer` *required*
>
> The unique agent identifier. Obtain this from the List Projects action.
>
> **crawlStatus** `string ("all" | "ok" | "failed" | "n/a" | "queued" | "limited")`
>
> Status values for crawl and index operations.
>
> **indexStatus** `string ("all" | "ok" | "failed" | "n/a" | "queued" | "limited")`
>
> Status values for crawl and index operations.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Persona Versions
>
> **Slug:** `CUSTOMGPT_LIST_PERSONAS`
>
> Tool to list persona versions for a CustomGPT agent. Use when you need to view the version history of an agent's persona. Every time the persona is updated, a snapshot is automatically saved, allowing you to view changes over time or restore a previous version. Results are paginated. Requires Custom plan.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number to return (≥1). If not specified, returns the first page.
>
> **limit** `integer`
>
> Limit the number of persona versions to return per page. Defaults to 20.
>
> **project\_id** `integer` *required*
>
> The unique agent identifier. Obtain this from the List Projects action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List CustomGPT Project Licenses
>
> **Slug:** `CUSTOMGPT_LIST_PROJECT_LICENSES`
>
> List licenses for a CustomGPT project or agent using its numeric project ID. Use this to check the project's license records and their details, such as type, status, and timestamps.
>
> #### Input Parameters
>
> **projectId** `string` *required*
>
> The unique identifier of the CustomGPT project (agent). Must be a numeric ID (e.g., '90631').
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List CustomGPT Projects
>
> **Slug:** `CUSTOMGPT_LIST_PROJECTS`
>
> Lists all CustomGPT projects (agents) for the authenticated user. Returns projects with full details including ID, name, type, chat status, and timestamps. Supports pagination via the 'page' parameter. Use this to discover available projects or iterate through all projects.
>
> #### Input Parameters
>
> **page** `integer`
>
> Page number for pagination (≥1). If not specified, returns the first page. Results are sorted by creation date (newest first).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Agent Sources
>
> **Slug:** `CUSTOMGPT_LIST_SOURCES`
>
> Tool to list all data sources connected to an agent. Returns sources from various origins like sitemaps, Google Drive folders, SharePoint sites, or uploaded files. Use this to manage what content feeds into an agent's knowledge base.
>
> #### Input Parameters
>
> **project\_id** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Reindex Page
>
> **Slug:** `CUSTOMGPT_REINDEX_PAGE`
>
> Starts reindexing a URL-based document in a CustomGPT knowledge base to update its content. The response indicates whether the update process started.
>
> #### Input Parameters
>
> **pageId** `integer` *required*
>
> The page id of the document to reindex.
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Team Members
>
> **Slug:** `CUSTOMGPT_SEARCH_TEAM_MEMBERS`
>
> Tool to search for team members by email address or user ID. Use this to find users when assigning permissions or managing team access. Requires Owner or Admin role to execute.
>
> #### Input Parameters
>
> **email** `string`
>
> Email address of the team member to search for. Use this to find users by their email.
>
> **user\_id** `integer`
>
> User ID of the team member to search for. Use this to find users by their numeric ID.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Submit Message Feedback
>
> **Slug:** `CUSTOMGPT_SUBMIT_MESSAGE_FEEDBACK`
>
> Tool to submit feedback (thumbs up/down) for a message in a CustomGPT conversation. Use this to record user satisfaction signals that help identify which AI responses are helpful and which need improvement. Feedback can be changed by submitting a new reaction value.
>
> #### Input Parameters
>
> **promptId** `integer` *required*
>
> The unique identifier of the message to submit feedback for. Obtained from listing conversation messages.
>
> **reaction** `string ("neutral" | "disliked" | "liked")` *required*
>
> The feedback reaction to record for this message. Use 'liked' for positive feedback, 'disliked' for negative feedback, or 'neutral' to clear existing feedback.
>
> **projectId** `integer` *required*
>
> The ID of the agent (project) containing the message.
>
> **sessionId** `string` *required*
>
> The session ID (UUID format) of the conversation containing the message. Obtained when creating or listing conversations.
>
> **includeInsights** `array`
>
> Optional list of fields to expand in the response for additional insights.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Page Metadata
>
> **Slug:** `CUSTOMGPT_UPDATE_PAGE_METADATA`
>
> Updates metadata for a specific page in a CustomGPT project, including its title, description, URL, and image.
>
> #### Input Parameters
>
> **url** `string`
>
> The url of the document used in citations. Maximum 2000 characters.
>
> **image** `string`
>
> The url of the image used in citations. Maximum 2000 characters.
>
> **title** `string`
>
> The title of the document used in citations. Maximum 255 characters.
>
> **pageId** `integer` *required*
>
> The id of a page in which metadata will be updated.
>
> **projectId** `integer` *required*
>
> The id of an agent (formerly known as project) in which page is stored. Obtain this from the List Projects action.
>
> **description** `string`
>
> The description of the document used in citations. Maximum 500 characters. Should be one to two sentences.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Project
>
> **Slug:** `CUSTOMGPT_UPDATE_PROJECT`
>
> Updates an existing CustomGPT agent's name or project configuration, including sharing, sitemap, license, and document-processing settings. Returns updated project details.
>
> #### Input Parameters
>
> **is\_shared** `boolean`
>
> Whether the agent is public or not. Set to true to make the agent publicly accessible.
>
> **project\_id** `integer` *required*
>
> The unique identifier of the agent (formerly known as project) to update.
>
> **project\_name** `string`
>
> Agent name to update. Use this to rename the agent.
>
> **sitemap\_path** `string`
>
> Sitemap path for the agent. Provide a URL to a sitemap XML file.
>
> **is\_anonymized** `boolean`
>
> Whether the agent should anonymize user data. Set to true to enable data anonymization.
>
> **is\_ocr\_enabled** `boolean`
>
> Whether OCR (Optical Character Recognition) is enabled for document processing.
>
> **file\_data\_retension** `boolean`
>
> Whether to retain file data after processing. Set to true to keep uploaded files.
>
> **are\_licenses\_allowed** `boolean`
>
> Whether project licenses are allowed. Set to true to enable license management for this agent.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Project License
>
> **Slug:** `CUSTOMGPT_UPDATE_PROJECT_LICENSE`
>
> Updates the name of an existing license for a CustomGPT project/agent. Prerequisites: - The project must have licenses enabled in its plan - Both project ID and license ID must be valid and exist - Use List Projects to get valid project IDs - Use List Project Licenses to get valid license IDs for a project This action only updates the license name. Other license properties cannot be modified through this endpoint.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The new name to assign to the license (1-255 characters recommended)
>
> **licenseId** `string` *required*
>
> Unique identifier of the license to update. Obtain this from the List Project Licenses action.
>
> **projectId** `string` *required*
>
> Numeric ID of the CustomGPT project/agent (as string). Obtain this from the List Projects action.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Project Settings
>
> **Slug:** `CUSTOMGPT_UPDATE_PROJECT_SETTINGS`
>
> Update CustomGPT agent configuration settings. Updates persona instructions, response format, citation style, branding, and deployment settings. Only include fields you want to change - omitted fields retain their current values. Use this to configure agent behavior, customize appearance, or adjust user experience settings.
>
> #### Input Parameters
>
> **projectId** `integer` *required*
>
> The unique identifier of the agent/project whose settings to update
>
> **chat\_bot\_bg** `object`
>
> Background image file for the agent widget.
>
> **font\_family** `string ("inter" | "public-sans")`
>
> Font family options for the agent.
>
> **user\_avatar** `object`
>
> User avatar image file.
>
> **chatbot\_color** `string`
>
> Primary color for the agent in hex format (e.g., '#000000')
>
> **chatbot\_model** `string ("gpt-4-1" | "gpt-4-o" | "gpt-5-chat" | "gpt-5.1-none" | "gpt-5.1-low" | "gpt-5.2-none" | "gpt-5.2-low" | "gpt-4-1-mini" | "gpt-4o-mini" | "claude-4.5-opus" | "claude-4.5-sonnet" | "claude-4-sonnet" | "claude-4.5-haiku" | "claude-3.5-sonnet" | "gpt-o4-mini-low" | "gpt-o4-mini-medium" | "gpt-o4-mini-high" | "gemini-3-pro" | "gemini-2.5-flash")`
>
> AI models available for the agent.
>
> **chatbot\_title** `string`
>
> Title displayed for the agent
>
> **view\_less\_msg** `string`
>
> Text for 'view less' button in starter questions
>
> **view\_more\_msg** `string`
>
> Text for 'view more' button in starter questions
>
> **default\_prompt** `string`
>
> Default prompt or welcome message shown to users
>
> **ending\_message** `string`
>
> Text appended to every agent response
>
> **radius\_styling** `string ("sharp" | "soft" | "round" | "legacy")`
>
> Radius styling options for the agent.
>
> **user\_awareness** `boolean`
>
> Whether agent is aware of logged-in user's name
>
> **chat\_bot\_avatar** `object`
>
> Avatar image file for the agent.
>
> **remove\_branding** `boolean`
>
> Whether to remove CustomGPT branding from the agent
>
> **response\_source** `string ("default" | "own_content" | "openai_content")`
>
> Response source configuration options.
>
> **agent\_capability** `string ("fastest-responses" | "optimal-choice" | "advanced-reasoning" | "complex-tasks")`
>
> Agent capability levels for processing user queries.
>
> **chat\_bot\_bg\_type** `string ("image" | "color")`
>
> Background type for the agent widget.
>
> **chatbot\_msg\_lang** `string ("sq" | "ar" | "hy" | "az" | "ba" | "eu" | "be" | "bn" | "bh" | "bs" | "pt-BR" | "bg" | "yue" | "ca" | "hne" | "hr" | "cs" | "da" | "doi" | "nl" | "en" | "et" | "fo" | "fi" | "fr" | "gl" | "ka" | "de" | "el" | "gu" | "hry" | "he" | "hi" | "hu" | "id" | "ga" | "it" | "ja" | "jv" | "kn" | "ks" | "kk" | "kok" | "ko" | "ky" | "lv" | "lt" | "mk" | "mai" | "ms" | "mt" | "cmn" | "mr" | "mwr" | "nan" | "mo" | "mn" | "me" | "ne" | "no" | "or" | "ps" | "fa" | "pl" | "pt" | "pa" | "raj" | "ro" | "ru" | "sa" | "sat" | "sr" | "sd" | "si" | "sk" | "sl" | "es" | "sw" | "sv" | "tg" | "ta" | "tt" | "te" | "th" | "tr" | "tk" | "uk" | "ur" | "uz" | "vi" | "cy" | "wuu")`
>
> Language codes for agent interface messages.
>
> **enable\_citations** `integer`
>
> Citation display setting (0-3 scale)
>
> **enable\_feedbacks** `boolean`
>
> Whether to show thumbs up/down feedback buttons
>
> **is\_hybrid\_search** `boolean`
>
> Whether to enable enhanced search for numeric codes (may slow responses)
>
> **markdown\_enabled** `boolean`
>
> Whether to enable Markdown formatting in responses
>
> **spotlight\_avatar** `object`
>
> Spotlight avatar image file.
>
> **chat\_bot\_bg\_color** `string`
>
> Background color in hex format (e.g., '#FFFFFF')
>
> **example\_questions** `array`
>
> List of example questions to guide users
>
> **hang\_in\_there\_msg** `string`
>
> Message shown while agent is processing a response
>
> **no\_answer\_message** `string`
>
> Message shown when agent cannot answer a question
>
> **chatbot\_siesta\_msg** `string`
>
> Message shown when the agent encounters an error
>
> **is\_selling\_enabled** `boolean`
>
> Whether agent monetization is enabled
>
> **chatbot\_title\_color** `string`
>
> Color for the agent title in hex format
>
> **citations\_view\_type** `string ("user" | "show" | "hide")`
>
> Citation display control options.
>
> **user\_avatar\_enabled** `boolean`
>
> Whether to enable user avatar display
>
> **input\_field\_addendum** `string`
>
> Additional text for input field (e.g., Terms of Service URL)
>
> **persona\_instructions** `string`
>
> System instructions defining agent personality and behavior
>
> **title\_avatar\_enabled** `boolean`
>
> Whether to show avatar next to title
>
> **chat\_bot\_color\_scheme** `string ("fresh" | "legacy")`
>
> Color scheme options for the agent.
>
> **chatbot\_toolbar\_color** `string`
>
> Color for the agent toolbar in hex format
>
> **spotlight\_avatar\_type** `string ("default" | "image")`
>
> Spotlight avatar type options.
>
> **can\_share\_conversation** `boolean`
>
> Whether users can share conversations
>
> **image\_citation\_display** `string ("default" | "first_only")`
>
> Image citation display options.
>
> **spotlight\_avatar\_shape** `string ("circle" | "rectangle")`
>
> Spotlight avatar shape options.
>
> **can\_export\_conversation** `boolean`
>
> Whether users can export conversations
>
> **user\_avatar\_orientation** `string ("agent-left-user-right" | "agent-right-user-right" | "agent-right-user-left" | "agent-left-user-left")`
>
> Avatar orientation options.
>
> **conversation\_time\_window** `integer`
>
> Conversation activity window: 0=24hr memory limit, 1=unlimited, 2=close after 24hrs
>
> **spotlight\_avatar\_enabled** `boolean`
>
> Whether to enable spotlight avatar display
>
> **try\_asking\_questions\_msg** `string`
>
> Message encouraging users to ask example questions
>
> **citations\_sources\_label\_msg** `string`
>
> Label text for the sources section
>
> **conversation\_retention\_days** `integer`
>
> Custom retention period in days for conversations (used when retention\_period is 'custom')
>
> **enable\_inline\_citations\_api** `boolean`
>
> Whether citations appear inline within responses
>
> **hide\_sources\_from\_responses** `boolean`
>
> Whether to hide source names in agent responses
>
> **limit\_image\_citation\_height** `boolean`
>
> Whether to limit the height of image citations
>
> **agent\_title\_avatar\_alignment** `string ("left" | "center" | "right")`
>
> Agent title and avatar alignment options.
>
> **is\_loading\_indicator\_enabled** `boolean`
>
> Whether to show loading animation while waiting for response
>
> **use\_opengraph\_image\_citation** `boolean`
>
> Whether to use OpenGraph images from source pages in citations
>
> **chatbot\_failed\_moderation\_msg** `string`
>
> Message shown when content fails moderation checks
>
> **conversation\_retention\_period** `string ("custom" | "year" | "never")`
>
> Conversation retention period options.
>
> **citations\_answer\_source\_label\_msg** `string`
>
> Label text for the answer source indicator
>
> **use\_context\_aware\_starter\_question** `boolean`
>
> Whether to generate context-aware starter questions
>
> **enable\_recaptcha\_for\_public\_chatbots** `boolean`
>
> Whether to use reCAPTCHA for public agent access
>
> **enable\_agent\_knowledge\_base\_awareness** `boolean`
>
> Whether agent is aware of its knowledge base scope
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Source Settings
>
> **Slug:** `CUSTOMGPT_UPDATE_SOURCE`
>
> Update settings for a CustomGPT agent data source, including auto-sync frequency, refresh behavior, JavaScript execution, image extraction, page creation and removal, and custom refresh schedules.
>
> #### Input Parameters
>
> **source\_id** `integer` *required*
>
> The unique identifier of the data source to update.
>
> **project\_id** `integer` *required*
>
> The unique identifier of the agent (formerly known as project).
>
> **executive\_js** `boolean`
>
> Whether the agent source should execute JavaScript when crawling web pages.
>
> **create\_new\_pages** `boolean`
>
> Add new pages to agent automatically during refresh agent source.
>
> **refresh\_schedule** `object`
>
> Custom schedule configuration for advanced data refresh frequency.
>
> **allow\_extra\_timeout** `boolean`
>
> Allow extra timeout for agent source during crawling operations.
>
> **remove\_unexist\_pages** `boolean`
>
> Remove pages from agent automatically during refresh agent source if they no longer exist.
>
> **image\_extraction\_type** `string ("none" | "sync_from_sitemap")`
>
> Method used for extracting images from the website.
>
> **data\_refresh\_frequency** `string ("never" | "daily" | "weekly" | "monthly" | "advanced")`
>
> Data refresh frequency options for source auto-sync.
>
> **refresh\_existing\_pages** `string ("never" | "always" | "if_updated")`
>
> Options for refreshing existing pages during source sync.
>
> **update\_existing\_images** `boolean`
>
> Whether to update existing images during refresh operations.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update User Profile
>
> **Slug:** `CUSTOMGPT_UPDATE_USER_PROFILE`
>
> Updates the authenticated user's profile information in CustomGPT. Use this action to modify profile details such as the user's display name, email address, or profile photo URL. All fields are optional - only the fields you provide will be updated. The action returns the complete updated user profile.
>
> #### Input Parameters
>
> **name** `string`
>
> The user's full display name. Can include special characters and Unicode.
>
> **email** `string`
>
> The user's email address for account identification and notifications.
>
> **profile\_photo\_url** `string`
>
> URL pointing to the user's profile photo. Note: CustomGPT may auto-generate profile photos based on initials instead of using custom URLs.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Verify Message Accuracy
>
> **Slug:** `CUSTOMGPT_VERIFY_MESSAGE`
>
> Trigger verification of a message in a CustomGPT conversation. The response can include a confirmation message and status.
>
> #### Input Parameters
>
> **promptId** `integer` *required*
>
> The message ID of the message to verify.
>
> **projectId** `integer` *required*
>
> The ID of the agent (project) to verify the message for.
>
> **sessionId** `string` *required*
>
> The session ID of the conversation containing the message to verify.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
