What is Rube MCP in plain-automation?

Rube MCP is the MCP server interface used to discover tools and execute Composio Plain tasks. You connect to it at https://rube.app/mcp.

Why must I call RUBE_SEARCH_TOOLS first?

Tool schemas change over time. Calling RUBE_SEARCH_TOOLS fetches the current available tools, their slugs, input schemas, and execution plans so you don’t hardcode outdated values.

Do I need to include memory in every tool execution?

Yes. RUBE_MULTI_EXECUTE_TOOL calls must include a memory object, even if empty ({}), to satisfy the schema and preserve state as needed.

plain-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Plain Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/plain

Prerequisites

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

Step 2: Check Connection

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

Overview

Plain Automation via Rube MCP automates Plain operations using Composio's Plain toolkit. It relies on discovering current tool schemas with RUBE_SEARCH_TOOLS and ensuring an active Plain connection through RUBE_MANAGE_CONNECTIONS. This workflow enables dynamic tool execution without hardcoding slugs.

How This Skill Works

The skill connects to an MCP server at https://rube.app/mcp, verifies the availability of RUBE_SEARCH_TOOLS, and discovers tools for a given Plain task. It then checks that the Plain connection is ACTIVE and executes the chosen tool with RUBE_MULTI_EXECUTE_TOOL, always including a memory object and a session_id.

When to Use It

When you need to automate a Plain operation and must use the latest tool schemas before execution.
When setting up a workflow that requires validating an active Plain connection prior to running tools.
When you need to discover available Plain tools before selecting a slug to execute.
When executing a tool and ensuring you pass a session_id and memory payload as part of the call.
When reusing a session across multiple steps in a single Plain automation workflow.

Quick Start

Step 1: Add the MCP endpoint https://rube.app/mcp in your client and verify RUBE_SEARCH_TOOLS responds.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["plain"] and ensure the connection status is ACTIVE.
Step 3: Discover tools with RUBE_SEARCH_TOOLS for your Plain task, then execute a chosen tool via RUBE_MULTI_EXECUTE_TOOL with memory: {} and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas and avoid hardcoding slugs.
Verify that the RUBE_MANAGE_CONNECTIONS status is ACTIVE before executing any tools.
Use exact field names and types from the tool schemas returned by RUBE_SEARCH_TOOLS.
Always include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
Reuse session IDs within a workflow and generate new ones for new workflows to prevent conflicts.

Example Use Cases

Discover a Plain tool via RUBE_SEARCH_TOOLS for a data normalization task, then execute it with the proper input and an active session.
Set up a Plain automation by connecting to the toolkit, confirm ACTIVE status, and run a 'clean_data' tool with required arguments.
Create a multi-step Plain workflow: search tools, manage connection, and execute a discovered tool using a session_id and memory, reusing the session for subsequent steps.
If tool schemas change, re-fetch tool schemas before each run to ensure correct field names and types.
Use RUBE_REMOTE_WORKBENCH to run a batch of Plain tools in bulk, leveraging run_composio_tool for efficiency.

Frequently Asked Questions

Add this skill to your agents