What is Rube MCP in this skill?

Rube MCP is the MCP endpoint used to manage and run Composio Cats tools via a structured set of commands (RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL).

Do I need API keys for MCP?

No API keys are needed — you simply add the MCP endpoint (e.g., https://rube.app/mcp) and proceed.

What if tool schemas change?

Always fetch current schemas with RUBE_SEARCH_TOOLS before execution and avoid hardcoding slugs or arguments; ensure inputs match the schema exactly and include memory in executions.

cats-automation

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

Files (1)

SKILL.md

2.8 KB

Cats Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/cats

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Cats connection via RUBE_MANAGE_CONNECTIONS with toolkit cats
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 cats
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: "Cats 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 Cats task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["cats"]
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 Cats-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `cats`
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/cats-automation/SKILL.mdView on GitHub

Overview

Automates Cats operations through Composio's Cats toolkit using Rube MCP. It emphasizes fetching up-to-date tool schemas with RUBE_SEARCH_TOOLS and ensuring an ACTIVE Cats connection before executing workflows.

How This Skill Works

Discover available Cats tools with RUBE_SEARCH_TOOLS, then establish and verify an ACTIVE Cats connection via RUBE_MANAGE_CONNECTIONS. Finally, execute the chosen tool using RUBE_MULTI_EXECUTE_TOOL, providing the correct input arguments, a memory payload, and a valid session_id.

When to Use It

You need to run a Cats operation discovered at runtime from tool schemas.
You must verify RUBE_SEARCH_TOOLS is available and fetch current tool schemas before execution.
You need to establish an ACTIVE Cats connection before starting a workflow.
You want to execute a discovered tool with proper arguments using RUBE_MULTI_EXECUTE_TOOL.
You are handling multi-tool workflows or paginated tool results.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration and confirm RUBE_SEARCH_TOOLS responds.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkit 'cats' and verify the STATUS is ACTIVE.
Step 3: Use RUBE_SEARCH_TOOLS to discover a tool, then execute it with RUBE_MULTI_EXECUTE_TOOL, including memory and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS before executing tools.
Verify the Cats connection status is ACTIVE with RUBE_MANAGE_CONNECTIONS before running workflows.
Use exact field names and types from the search results when wiring inputs.
Include memory: {} in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
Reuse session IDs within a workflow; generate new ones for new workflows.

Example Use Cases

Discover tools for Cats operations with RUBE_SEARCH_TOOLS, then execute the returned tool slug with correct arguments in a single session.
Connect to the Cats toolkit via RUBE_MANAGE_CONNECTIONS and ensure the status is ACTIVE before running any workflow.
Fetch full tool schemas using RUBE_GET_TOOL_SCHEMAS and tailor your inputs to the exact schema.
Run multiple tools in a single workflow by sequencing RUBE_MULTI_EXECUTE_TOOL calls with memory and session_id.
When tool listings are large, handle pagination tokens from RUBE_SEARCH_TOOLS and continue fetching until complete.

Frequently Asked Questions

Add this skill to your agents