What is Rube MCP used for?

Rube MCP provides a centralized control plane to discover, connect, and execute Customgpt tools described by Composio tool schemas.

Do I need API keys to use MCP?

No API keys are required; you add the MCP endpoint (https://rube.app/mcp) in your client configuration and authenticate via the provided workflow.

How do I handle changing tool schemas?

Always re-run RUBE_SEARCH_TOOLS to fetch current tool slugs and required input fields before executing any tools.

customgpt-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Customgpt Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/customgpt

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Customgpt operations through Composio's toolkit via Rube MCP. It emphasizes discovering current tool schemas before execution and ensuring an active connection. This keeps workflows aligned with up-to-date capabilities.

How This Skill Works

You discover available tools with RUBE_SEARCH_TOOLS, then verify the connection using RUBE_MANAGE_CONNECTIONS. Once confirmed, you execute the chosen tool through RUBE_MULTI_EXECUTE_TOOL, always including memory and a session_id to maintain context.

When to Use It

When you need to automate a Customgpt task and rely on the latest available tools
When tool schemas change and you must fetch current slugs and arguments
When you need to validate an active connection before execution
When performing batch tool executions in one session using memory and session reuse
When you want to bulk-operate with RUBE_MULTI_EXECUTE_TOOL and avoid hardcoding slugs

Quick Start

Step 1: Add rube MCP as an MCP server: https://rube.app/mcp
Step 2: Run RUBE_SEARCH_TOOLS to discover available Customgpt tools
Step 3: Check connection with RUBE_MANAGE_CONNECTIONS and then execute tools via RUBE_MULTI_EXECUTE_TOOL, including memory and session_id

Best Practices

Always call RUBE_SEARCH_TOOLS before any workflow to fetch current tool slugs and schemas
Verify RUBE_MANAGE_CONNECTIONS reports ACTIVE before executing tools
Use exact field names and types from the tool schemas retrieved by RUBE_SEARCH_TOOLS
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even when empty
Reuse session IDs within a workflow and handle pagination tokens if provided

Example Use Cases

Automate a content-generation task by discovering a GENERATE_CONTENT tool and running it with memory
Transform customer data with a DATA_TRANSFORM tool after ensuring ACTIVE connection
Validate outputs using a VALIDATE_OUTPUT tool then route results
Update a Customgpt index by running UPDATE_EMBEDDINGS with the found tool
Run a sequence of tools with RUBE_MULTI_EXECUTE_TOOL in a single session and reuse session_id

Frequently Asked Questions

Add this skill to your agents