- Category: ai agents
- Auth: NO_AUTH
- Composio-managed OAuth available? N/A
- Tools: 19
- Triggers: 0
- Slug:
COMPOSIO - Version: 20260917_00
Tools
Check active connection (deprecated)
Check active connection (deprecated)
Slug:
COMPOSIO_CHECK_ACTIVE_CONNECTIONDeprecated: use check active connections instead for bulk operations. check active connection status for a toolkit or specific connected account id. returns connection details if active, or required parameters for establishing connection if none exists. active connections enable agent actions on the toolkit.Input Parameters
Output
Check multiple active connections
Check multiple active connections
Slug:
COMPOSIO_CHECK_ACTIVE_CONNECTIONSCheck active connection status for multiple toolkits or specific connected account ids. returns connection details if active, or required parameters for establishing connection if none exists. active connections enable agent actions on toolkits.Input Parameters
Output
Create Plan
Create Plan
Slug:
COMPOSIO_CREATE_PLANIMPORTANT - ALWAYS CALL THIS AFTER MANAGE CONNECTIONS TOOL IS EXECUTED. You are an efficient workflow builder, your job is to guide the LLM to create a plan for the given use_caseInput Parameters
Detailed explanation of the use case the user is trying to accomplish. Include as many details as possible for a better plan
Reasoning from the search about the use case and how the selected tools can accomplish it
Difficulty level for the plan. Choose “easy” for simple tasks (send email to known email id), “medium” for moderate complexity (summarize slack messages from last day), and “hard” for complex tasks requiring multiple steps or advanced logic (create personalized draft for 100 emails).
CRITICAL: Session identifier for workflow correlation and tracking across multiple tool calls. While technically optional, this parameter should ALWAYS be passed from RUBE_SEARCH_TOOLS response. Used to maintain context and enable proper workflow execution monitoring across the entire workflow chain.
Provide any workflow inputs you already know (e.g. channel name, user email, timezone). This helps the tool infer or look up missing details (for example, finding channel_id from a given channel_name). Keep values short and structured—do not include long texts like full messages. Example: [“channel_name:pod-sdk”, “channel_id:123”, “user_name:John”, “timezone:Asia/Kolkata”]
List of primary tool slugs that can accomplish the main task. For example: [‘GITHUB_LIST_PULL_REQUESTS’, ‘SLACK_SEND_MESSAGE’]
List of related/supporting tool slugs that might be useful. These are optional tools that could help with the task.
Output
Enable trigger
Enable trigger
Execute Composio Tool
Execute Composio Tool
Slug:
COMPOSIO_EXECUTE_TOOLExecute a tool using the composio api.Input Parameters
Whether to allow destructive tools to be executed. If true, the tool will be executed even if it is destructive.
The arguments to be passed to the tool. The schema of the arguments is present in the retrieve_actions response
The ID of the connected account to use. If not provided, uses the first active connection for the toolkit
The slug of the tool to execute, to be used from the list of tools retrieved using retrieve_actions
Output
Get Tool Dependency Graph
Get Tool Dependency Graph
Slug:
COMPOSIO_GET_DEPENDENCY_GRAPHGet the dependency graph for a given tool, showing related parent tools that might be useful. this action calls the composio labs dependency graph api to retrieve tools that are commonly used together with or before the specified tool. this helps discover related tools and understand common workflows.Input Parameters
Output
Get required parameters for connection
Get required parameters for connection
Slug:
COMPOSIO_GET_REQUIRED_PARAMETERSGets the required parameters for connecting to a toolkit via initiate connection. returns the exact parameter names and types needed for initiate connection’s parameters field. supports api keys, oauth credentials, connection fields, and hybrid authentication scenarios. if has default credentials is true, you can call initiate connection with empty parameters for seamless oauth flow.Input Parameters
Name of the toolkit to analyze for authentication requirements. Returns parameters for API keys, OAuth credentials, or connection fields needed by initiate_connection.
Output
Get response schema
Get response schema
Slug:
COMPOSIO_GET_RESPONSE_SCHEMARetrieves the response schema for a specified composio tool. this action fetches the complete response schema definition for any valid composio tool, returning it as a dictionary that describes the expected response structure.Input Parameters
Name of the tool. For example: GITHUB_LIST_PULL_REQUESTS. You can find the relevant tool names using COMPOSIO_RETRIEVE_ACTIONS tool.
Output
Initiate connection
Initiate connection
Slug:
COMPOSIO_INITIATE_CONNECTIONInitiate a connection to a toolkit with comprehensive authentication support. supports all authentication scenarios: 1. composio default oauth (no parameters needed) 2. custom oauth (user’s client id/client secret) 3. api key/bearer token authentication 4. basic auth (username/password) 5. hybrid scenarios (oauth + connection fields like site name) 6. connection-only fields (subdomain, api key at connection level) 7. no authentication required automatically detects and validates auth config vs connection fields, provides helpful error messages for missing parameters.Input Parameters
Authentication parameters for the connection. Structure depends on auth type: API Key Auth: {“generic_api_key”: “your_key”} Bearer Token: {“bearer_token”: “your_token”} or {“access_token”: “your_token”} Basic Auth: {“username”: “user”, “password”: “pass”} Custom OAuth: {“client_id”: “your_id”, “client_secret”: “your_secret”} Connection Fields: {“subdomain”: “your_subdomain”, “site_name”: “your_site”} Examples: - Exa: {“generic_api_key”: “your_exa_api_key”} - GitHub (token): {“access_token”: “ghp_xxxxx”} - Google Super (OAuth): {“client_id”: “xxx.apps.googleusercontent.com”, “client_secret”: “GOCSPX-xxx”} - SharePoint (hybrid): {“client_id”: “your_id”, “client_secret”: “your_secret”, “site_name”: “your_site”} - Zendesk (connection only): {“subdomain”: “your_subdomain”} Leave empty {} for default OAuth flow (if supported by toolkit). Use get_required_parameters action to see exact parameter names and requirements.
Output
List toolkits
List toolkits
List triggers
List triggers
Manage connections
Manage connections
Slug:
COMPOSIO_MANAGE_CONNECTIONSCreate or manage connections to user’s apps. Returns a branded authentication link that works for OAuth, API keys, and all other auth types.Call policy:- First call COMPOSIO_SEARCH_TOOLS for the user’s query.
- If COMPOSIO_SEARCH_TOOLS indicates there is no active connection for a toolkit, call COMPOSIO_MANAGE_CONNECTIONS with the exact toolkit name(s) returned.
- Use exact toolkit slugs returned by COMPOSIO_SEARCH_TOOLS; never invent toolkit names.
- NEVER execute any toolkit tool without an ACTIVE connection.
- If a connection is Active, the tool returns the connection details. Always use this to verify connection status and fetch metadata.
- If a connection is not Active, returns a authentication link (redirect_url) to create new connection.
- If reinitiate_all is true, the tool forces reconnections for all toolkits, even if they already have active connections.
- Always show the returned redirect_url as a FORMATTED MARKDOWN LINK in your final response for this turn as intermediate messages may be hidden or summarized by the chat interface, so the user may not see the link there. Ask the user to click on the link to finish authentication and reply when done.
- After the user replies, use COMPOSIO_MANAGE_CONNECTIONS to verify that the connection they just authorized is active.
- Begin executing tools only after the connection for that toolkit is confirmed Active.
Input Parameters
Toolkit slugs to check or connect. Must be valid toolkit slugs; never invent. Missing connections initiate auth. Examples: [‘gmail’, ‘github’, ‘slack’, ‘googlesheets’, ‘outlook’].
Force reconnection for all listed toolkits, even if active connections already exist. Use when credentials may be stale, you need fresh credentials/settings, or you are troubleshooting connection issues. This replaces existing active connections with new auth-link flows. Default false.
Output
Multi Execute Composio Tools
Multi Execute Composio Tools
Slug:
COMPOSIO_MULTI_EXECUTE_TOOLFast and parallel tool executor for tools discovered through COMPOSIO_SEARCH_TOOLS. Use this tool to execute up to 50 tools in parallel across apps only when they’re logically independent (no ordering/output dependencies). Response contains structured outputs ready for immediate analysis - avoid reprocessing them via remote bash/workbench tools.Prerequisites:- Always use valid tool slugs and their arguments. NEVER invent tool slugs or argument fields. ALWAYS pass STRICTLY schema-compliant arguments with each tool execution.
- Ensure an ACTIVE connection exists for the toolkits that are going to be executed. If none exists, MUST initiate one via COMPOSIO_MANAGE_CONNECTIONS before execution.
- Only batch tools that are logically independent - no ordering, no output-to-input dependencies, and no intra-call chaining (tools in one call can’t use each other’s outputs). DO NOT pass dummy or placeholder inputs; always resolve required inputs using appropriate tools first.
- If COMPOSIO_SEARCH_TOOLS returns a tool that can perform the task, prefer calling it via this executor. Do not write custom API calls or ad-hoc scripts for tasks that can be completed by available Composio tools.
- Prefer parallel execution: group independent tools into a single multi-execute call where possible.
- Predictively set sync_response_to_workbench=true if the response may be large or needed for later scripting. It still shows response inline; if the actual response data turns out small and easy to handle, keep everything inline and SKIP workbench usage.
- Responses contain structured outputs for each tool. RULE: Small data - process yourself inline; large data - process in the workbench.
- ALWAYS include inline references/links to sources in MARKDOWN format directly next to the relevant text. Eg provide slack thread links alongside with summary, render document links instead of raw IDs.
- CRITICAL: You MUST always include the ‘memory’ parameter - never omit it. Even if you think there’s nothing to remember, include an empty object {} for memory.
- CRITICAL FORMAT: Memory must be a dictionary where keys are app names (strings) and values are arrays of strings. NEVER pass nested objects or dictionaries as values.
- CORRECT format: {“slack”: [“Channel general has ID C1234567”], “gmail”: [“John’s email is john@example.com”]}
- Write memory entries in natural, descriptive language - NOT as key-value pairs. Use full sentences that clearly describe the relationship or information.
- ONLY store information that will be valuable for future tool executions - focus on persistent data that saves API calls.
- STORE: ID mappings, entity relationships, configs, stable identifiers.
- DO NOT STORE: Action descriptions, temporary status updates, logs, or “sent/fetched” confirmations.
- Examples of GOOD memory (store these):
- “The important channel in Slack has ID C1234567 and is called #general”
- “The team’s main repository is owned by user ‘teamlead’ with ID 98765”
- “The user prefers markdown docs with professional writing, no emojis” (user_preference)
- Examples of BAD memory (DON’T store these):
- “Successfully sent email to john@example.com with message hi”
- “Fetching emails from last day (Sep 6, 2025) for analysis”
- Do not repeat the memories stored or found previously.
Input Parameters
Predictively set true when the response may be large or needed for later scripting. Saves the full response to the workbench while returning an inline preview. If the result is small, keep it inline. Default false.
CRITICAL: Memory must be a dictionary with app names as keys and string arrays as values. NEVER use nested objects. Format: {“app_name”: [“string1”, “string2”]}. Store durable facts - stable IDs, mappings, roles, preferences. Exclude ephemeral data like message IDs or temp links. Use full sentences describing relationships. Always include this parameter.
Short enum for current step of the workflow execution. Eg FETCHING_EMAILS, GENERATING_REPLIES. Always include to keep execution aligned with the workflow.
Progress metrics for the current step - use to track how far execution has advanced. Format as a string “done/total units” - example “10/100 emails”, “0/n messages”, “3/10 pages”.
Output
Run bash commands
Run bash commands
Slug:
COMPOSIO_REMOTE_BASH_TOOLExecute bash commands in a REMOTE sandbox for file operations, data processing, and system tasks. Essential for handling large tool responses saved to remote files. Hard 3-minute (180s) execution limit — break large tasks into smaller commands. PRIMARY USE CASES:- Process large tool responses saved by COMPOSIO_MULTI_EXECUTE_TOOL to remote sandbox
- File system operations, extract specific information from JSON with shell tools like jq, awk, sed, grep, etc.
- Commands run from /home/user directory by default
Input Parameters
The bash command to execute. Hard 3-minute (180s) execution limit — break large tasks into smaller commands.
Output
Execute Code remotely in work bench
Execute Code remotely in work bench
Slug:
COMPOSIO_REMOTE_WORKBENCHUse this persistent Jupyter sandbox only for remote files or scripted bulk tool executions. Do not use it for inline data, quick parsing or summaries, or basic math.USE IT TO- Parse or analyze tool outputs saved by COMPOSIO_MULTI_EXECUTE_TOOL, script multi-tool chains, or run known Composio tools in bulk.
- Call APIs via proxy_execute when no Composio tool exists for that API.
- Returns compact results; long outputs become artifacts under
/mnt/files/.composio/output(cloud-backed and persistent across sandbox restarts).
- Work stepwise. State persists across cells, including variables, functions, imports, and files. Save resumable checkpoints to
/mnt/files/and call this tool again for the next step. - Top-level cells cannot use
return; end withoutputorprint(output). - Each cell has a hard 180-second limit. Use
ThreadPoolExecutorfor bulk operations and split large data into batches across cells. - Schema safety: Never assume the response schema for run_composio_tool if not known already from previous tools. To inspect schema, either run a simple request outside the workbench or use invoke_llm helper.
- Use
invoke_llmfor summaries, analysis, or field extraction instead of ad hoc filtering. - Avoid Meta Loops: Do not use run_composio_tool to call COMPOSIO_* meta tools. Only use it for app tools.
- Paginate until no
next_page_tokenor cursor remains. Parallelize when page numbers are supported. - Never hardcode data; load it from files or tool responses and iterate to build outputs.
- For user-downloadable files, call
upload_local_file; never expose raw sandbox paths.
- Home:
/home/user. Do not import or redeclare these helpers:run_composio_tool(tool_slug: str, arguments: dict) -> tuple[Dict[str, Any], str]: Execute a known Composio app tool in loops, parallel, or bulk. Use an exact known name and schema. Results have top-level “data” and may be nested.invoke_llm(query: str, reasoning_effort: Optional[Literal["low","medium","high"]] = None) -> tuple[str, str]: Run semantic tasks with at most 200k characters. reasoning_effort is an optional hint passed to the model (some models ignore it); omit it unless a task clearly needs “high” reasoning. Define the exact output JSON schema and batch items into small groups. Use f-strings or concatenation to preserve literal braces; with str.format, escape them as {{ }}.upload_local_file(*file_paths) -> tuple[Dict[str, Any], str]: Upload user-downloadable artifacts to Composio S3/R2. Multiple files are auto-zipped; success data includes s3_url, uploaded_file, type, s3key, and message.proxy_execute(method: Literal["GET","POST","PUT","DELETE","PATCH"], endpoint, toolkit, query_params=None, body=None, headers=None) -> tuple[Any, str]: Call a toolkit API directly when no Composio tool exists. Only one toolkit can be invoked per workbench call.web_search(query: str) -> tuple[str, str]: Search the web for information.smart_file_extract(sandbox_file_path: str, show_preview: bool = True) -> tuple[str, str]: Extracts text from files in the sandbox (e.g., PDF, image).
- All helpers return
(result, error); always checkerrorbefore usingresult. - Parse responses defensively: inspect keys while narrowing because data can be nested.
- For bulk calls, use
ThreadPoolExecutorand set concurrency so the cell finishes within 180 seconds.
Input Parameters
Python to run inside the persistent remote Jupyter sandbox. State (imports, variables, files) is preserved across executions. Keep code concise. Avoid unnecessary comments. Hard 3-minute (180s) execution limit — break large tasks into smaller cells.
Short enum for current step of the workflow execution. Eg FETCHING_EMAILS, GENERATING_REPLIES. Always include to keep execution aligned with the workflow.
Progress metrics for the current step - use to track how far execution has advanced. Format as a string “done/total units” - example “10/100 emails”, “0/n messages”, “3/10 pages”.
Output
Search Composio Tools
Search Composio Tools
Slug:
COMPOSIO_SEARCH_TOOLSTool Server Info: Composio connects 500+ apps—Slack, GitHub, Notion, Google Workspace (Gmail, Sheets, Drive, Calendar), Microsoft (Outlook, Teams), X/Twitter, Figma, Web Search / Deep research, Browser tool (scrape URLs, browser automation), Meta apps (Instagram, Meta Ads), TikTok, and more—for seamless cross-app automation. Use this tool to discover relevant tools plus the recommended plan and common pitfalls for reliable execution. Always call this tool first whenever a user mentions or implies an external app, service, or workflow—never say “I don’t have access to X/Y app” before calling it.Usage guidelines:- Use this tool whenever kicking off a task. Re-run it when you need additional tools/plans due to missing details, errors, or a changed use case.
- Use search_strategy: “auto” normally. If the returned plan does not match the current request or an expected tool is missing, retry the same queries with search_strategy: “tool_search” to bypass cached plans and run direct tool search.
- If the user pivots to a different use case in same chat, you MUST call this tool again with the new use case and generate a new session_id.
- Specify the use_case with a normalized description of the problem, query, or task. Be clear and precise. Queries can be simple single-app actions or multiple linked queries for complex cross-app workflows.
- Pass known_fields along with use_case as a string of key–value hints (for example, “channel_name: general”) to help the search resolve missing details such as IDs.
- Atomic queries: 1 query = 1 tool call. Include hidden prerequisites (e.g., add “get Linear issue” before “update Linear issue”).
- Include app names: If user names a toolkit, include it in every sub query so intent stays scoped (e.g., “fetch Gmail emails”, “reply to Gmail email”).
- English input: Translate non-English prompts while preserving intent and identifiers.
- The response includes a detailed execution plan and common pitfalls. You MUST review this plan carefully, adapt it to your current context, and generate your own final step-by-step plan before execution. Execute the steps in order to ensure reliable and accurate execution. Skipping or ignoring required steps can lead to unexpected failures.
- Check the plan and pitfalls for input parameter nuances (required fields, IDs, formats, limits). Before executing any tool, you MUST review its COMPLETE input schema and provide STRICTLY schema-compliant arguments to avoid invalid-input errors.
- Determine whether pagination is needed; if a response returns a pagination token and completeness is implied, paginate until exhaustion and do not return partial results.
- Tools & Input Schemas: The response lists toolkits (apps) and tools suitable for the task, along with their tool_slug, description, input schema / schemaRef, and related tools for prerequisites, alternatives, or next steps.
- NOTE: Tools with schemaRef instead of input_schema require you to call COMPOSIO_GET_TOOL_SCHEMAS first to load their full input_schema before use.
- Connection Info: If a toolkit has an active connection, the response includes it along with any available current user information. If no active connection exists, you MUST initiate a new connection via COMPOSIO_MANAGE_CONNECTIONS with the correct toolkit name. DO NOT execute any toolkit tool without an ACTIVE connection.
- Time Info: The response includes the current UTC time for reference. You can reference UTC time from the response if needed.
- The tools returned to you through this are to be called via COMPOSIO_MULTI_EXECUTE_TOOL. Ensure each tool execution specifies the correct tool_slug and arguments exactly as defined by the tool’s input schema.
- The response includes a memory parameter containing relevant information about the use case and the known fields that can be used to determine the flow of execution. Any user preferences in memory must be adhered to.
Input Parameters
Structured English search queries to process in parallel. Split independent app/API actions into separate queries, including hidden prerequisites. Each query returns 4-6 tools.
Session context for correlating meta tool calls within a workflow. Always pass this parameter. Use {generate_id: true} for new workflows or {id: “EXISTING_ID”} to continue existing workflows.
Client LLM model name (recommended). Used to optimize planning/search behavior. Ignored if omitted or invalid.
Search path to use. Use auto normally. If the returned plan does not match the current request or an expected tool is missing, retry with tool_search to bypass cached plans and run direct tool search.
Output
Error if any occurred during the execution. Format: “X out of Y searches failed, reasons: <details>”
Wait for connection
Wait for connection
Wait for connection
Wait for connection
Slug:
COMPOSIO_WAIT_FOR_CONNECTIONSWait for user auth to finish. Call only after the user confirms they have completed authentication. Wait until mode=any/all toolkits reach a terminal state (ACTIVE/FAILED) or timeout.Example Input: { toolkits: [“gmail”,“outlook”], mode: “any” }Input Parameters
Wait for ANY connection or ALL connections to reach active/failed state (default: any)
Output
Get Tool Schemas
Get Tool Schemas
Slug:
COMPOSIO_GET_TOOL_SCHEMASRetrieve input schemas for tools by slug. Returns complete parameter definitions required to execute each tool. Only pass tool slugs returned by COMPOSIO_SEARCH_TOOLS — never guess or fabricate slugs. If unsure of the exact slug, call COMPOSIO_SEARCH_TOOLS first.Input Parameters
Schema fields to include. Defaults to [“input_schema”]. Include “output_schema” when calling tools in the workbench to validate response structure.