What is composio-search-automation?

A workflow to automate Composio Search tasks using Rube MCP and the composio_search toolkit.

What must I do before running tools?

Always call RUBE_SEARCH_TOOLS to fetch current tool schemas and ensure the connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.

How should memory and sessions be handled?

Include a memory object in RUBE_MULTI_EXECUTE_TOOL calls and reuse session IDs when appropriate; generate new sessions for new workflows.

composio-search-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/composio-search-automation --openclaw

Files (1)

SKILL.md

3.0 KB

Composio Search Automation via Rube MCP

Automate Composio Search operations through Composio's Composio Search toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/composio_search

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Composio Search connection via RUBE_MANAGE_CONNECTIONS with toolkit composio_search
Always call RUBE_SEARCH_TOOLS first 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_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit composio_search
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 Search 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 Search task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["composio_search"]
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_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, 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 Search-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `composio_search`
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-search-automation/SKILL.md

View on GitHub

Overview

Automates Composio Search tasks via Rube MCP using the composio_search toolkit. It emphasizes querying RUBE_SEARCH_TOOLS first to fetch current tool schemas and avoids hardcoding tool slugs.

How This Skill Works

Workflows start with discovering available tools through RUBE_SEARCH_TOOLS to obtain current schemas. Then verify the Composio connection via RUBE_MANAGE_CONNECTIONS and execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, including a memory payload as required.

When to Use It

When you must automate a sequence of Composio Search tasks and rely on the latest tool schemas fetched via RUBE_SEARCH_TOOLS.
When reusing a single session across multiple search steps in a workflow.
When ensuring the RUBE_MANAGE_CONNECTIONS ACTIVE status before executing tools.
When handling paginated search results and iterating with pagination tokens.
When performing batch operations with RUBE_REMOTE_WORKBENCH to run multiple tools in one job.

Quick Start

Step 1: Verify RUBE_SEARCH_TOOLS responds and fetch current schemas for composio_search.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["composio_search"] and ensure the session is ACTIVE.
Step 3: Use RUBE_MULTI_EXECUTE_TOOL with the discovered tool_slug and {memory: {}} to run the task.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas before any execution.
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before running tools.
Use exact field names and types from the discovered tool schemas; don’t hardcode slugs or args.
Always include a memory parameter in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
Reuse session IDs within a workflow when possible; generate new sessions only for new workflows.

Example Use Cases

Discover current Composio Search tools with RUBE_SEARCH_TOOLS, then execute a selected tool using the returned schema.
Establish an ACTIVE connection to composio_search and run a chained sequence of search tools within a single session.
Process a paginated search result set by looping until there are no more pages using the pagination token.
Run a batch of related search tools via RUBE_REMOTE_WORKBENCH to complete a larger data-retrieval task.
Save and reuse a session ID across several search steps to improve efficiency in a long-running task.

Frequently Asked Questions

Add this skill to your agents