composio-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/composio-automation --openclawComposio Automation via Rube MCP
Automate Composio operations through Composio's Composio toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/composio
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Composio connection via
RUBE_MANAGE_CONNECTIONSwith toolkitcomposio - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitcomposio - If connection is not ACTIVE, follow the returned auth link to complete setup
- Confirm connection status shows ACTIVE before running any workflows
Tool Discovery
Always discover available tools before executing workflows:
RUBE_SEARCH_TOOLS
queries: [{use_case: "Composio operations", known_fields: ""}]
session: {generate_id: true}
This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.
Core Workflow Pattern
Step 1: Discover Available Tools
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Composio task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["composio"]
session_id: "your_session_id"
Step 3: Execute Tools
RUBE_MULTI_EXECUTE_TOOL
tools: [{
tool_slug: "TOOL_SLUG_FROM_SEARCH",
arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
Known Pitfalls
- Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling
RUBE_SEARCH_TOOLS - Check connection: Verify
RUBE_MANAGE_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, even if empty ({}) - Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
- Pagination: Check responses for pagination tokens and continue fetching until complete
Quick Reference
| Operation | Approach |
|---|---|
| Find tools | RUBE_SEARCH_TOOLS with Composio-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit composio |
| Execute | RUBE_MULTI_EXECUTE_TOOL with discovered tool slugs |
| Bulk ops | RUBE_REMOTE_WORKBENCH with run_composio_tool() |
| Full schema | RUBE_GET_TOOL_SCHEMAS for tools with schemaRef |
Powered by Composio
Source
git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/composio-automation/SKILL.mdView on GitHub Overview
Composio Automation via Rube MCP lets you run Composio operations through the Composio toolkit from Rube. It emphasizes always discovering current tool schemas before execution to avoid stale tool slugs. The workflow covers setup, discovery, connection, and execution with proper session and memory handling.
How This Skill Works
Start by running RUBE_SEARCH_TOOLS to fetch Composio tool schemas. Then establish an active connection with RUBE_MANAGE_CONNECTIONS (toolkit: composio). Finally execute the discovered tool via RUBE_MULTI_EXECUTE_TOOL, supplying the correct args from the schema and a memory object for session state.
When to Use It
- Automating a recurring Composio operation via Rube MCP workflows
- When tool schemas may have changed, to fetch fresh slugs and fields
- Before executing tools, ensure the RUBE_MANAGE_CONNECTIONS status is ACTIVE
- Coordinating a sequence: discover tools -> connect -> execute in a session
- Performing bulk or batch Composio tasks with memory-aware tool execution
Quick Start
- Step 1: Add the Rube MCP endpoint (https://rube.app/mcp) as an MCP server
- Step 2: Run RUBE_SEARCH_TOOLS to verify tool schemas and available tool slugs
- Step 3: Run RUBE_MANAGE_CONNECTIONS with toolkit 'composio', then RUBE_MULTI_EXECUTE_TOOL with a discovered tool slug and memory object
Best Practices
- Always run RUBE_SEARCH_TOOLS before executing to get current schemas
- Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before any tool call
- Use exact field names and types from the search results; avoid hardcoding
- Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
- Reuse session IDs for related tasks and generate new ones for new workflows
Example Use Cases
- Automate a nightly Composio cleanup by discovering tools, connecting, and executing a cleanup tool slug
- Batch update of Composio entries by iterating discovered tool slugs in a single session
- Periodic reconciliation tasks that verify tool availability via RUBE_SEARCH_TOOLS
- Pre-deployment checks that verify an ACTIVE connection before running critical tools
- Bulk operations using RUBE_REMOTE_WORKBENCH with run_composio_tool() to execute multiple tools