What is required to start using magnetic-automation?

Add the Rube MCP endpoint (https://rube.app/mcp) in your client configuration and ensure RUBE_SEARCH_TOOLS can fetch tool schemas, then connect to the Magnetic toolkit.

Do I need API keys for Magnetic automation?

No API keys are needed. The MCP endpoint is used to access tools and schemas.

How do I handle changes in tool schemas?

Always call RUBE_SEARCH_TOOLS to retrieve current tool slugs and input schemas, and use the exact field names and types from those results; avoid hardcoding.

magnetic-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Magnetic Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/magnetic

Prerequisites

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

Step 2: Check Connection

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

Overview

This skill automates Magnetic operations by interfacing with Composio's Magnetic toolkit through Rube MCP. It emphasizes discovering current tool schemas before execution to avoid stale slugs or incorrect arguments, ensuring reliable automation workflows.

How This Skill Works

The workflow uses RUBE_SEARCH_TOOLS to fetch current Magnetic tool slugs and input schemas, then validates the connection with RUBE_MANAGE_CONNECTIONS (magnetic). Finally, it executes the chosen tool via RUBE_MULTI_EXECUTE_TOOL, supplying the correct arguments, a memory payload, and a session_id to maintain context across steps.

When to Use It

You need up-to-date Magnetic tool schemas before running any workflow
Starting a Magnetic automation and reusing a session across steps
Validating and establishing an ACTIVE connection to Magnetic via Rube MCP
Executing a batch of Magnetic tasks with discovered tool slugs
Troubleshooting tool schema changes or pagination in tool listings

Quick Start

Step 1: Add Rube MCP endpoint https://rube.app/mcp as an MCP server in your client config
Step 2: Run RUBE_SEARCH_TOOLS to fetch current Magnetic tool slugs and schemas
Step 3: Run RUBE_MANAGE_CONNECTIONS with toolkits: ["magnetic"] and then RUBE_MULTI_EXECUTE_TOOL with memory and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to get current tool schemas; never hardcode slugs or arguments
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results to ensure schema compliance
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow; generate a new one only for new workflows

Example Use Cases

Discover Magnetic tools via RUBE_SEARCH_TOOLS, then execute a selected tool with the correct input schema
Establish and verify ACTIVE Magnetic connection using RUBE_MANAGE_CONNECTIONS before running a workflow
Run multiple Magnetic tasks in sequence using RUBE_MULTI_EXECUTE_TOOL with a shared session_id
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to stay aligned with current capabilities
Reuse an existing session_id across a long Magnetic automation to preserve state and memory

Frequently Asked Questions

Add this skill to your agents