What is Rube MCP and how do I connect?

Rube MCP is the centralized management plane. Get started by adding https://rube.app/mcp as an MCP server in your client configuration; no API keys are required.

Why must I always search for tools before executing?

Tool schemas change regularly. Searching with RUBE_SEARCH_TOOLS ensures you use current tool slugs and correct argument structures.

How do I know my connection is ready to run?

Check RUBE_MANAGE_CONNECTIONS for the reply_io toolkit and confirm the status is ACTIVE before executing any workflows.

reply-io-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Reply IO Automation via Rube MCP

Automate Reply IO operations through Composio's Reply IO toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/reply_io

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["reply_io"]
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 Reply IO-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `reply_io`
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/reply-io-automation/SKILL.mdView on GitHub

Overview

Automate Reply IO tasks through Composio's Reply IO toolkit using Rube MCP. Always search for current tool schemas before executing to keep workflows aligned with live definitions.

How This Skill Works

Discover available tools with RUBE_SEARCH_TOOLS, then verify the connection via RUBE_MANAGE_CONNECTIONS. When ready, execute tools with RUBE_MULTI_EXECUTE_TOOL using the discovered tool_slug and exact schema fields, including an empty memory object. Maintain an active session_id and re-use it across related steps.

When to Use It

When starting a new Reply IO automation and need current tool schemas
Before running workflows, verify RUBE_MANAGE_CONNECTIONS is ACTIVE
Executing a multi-tool Reply IO workflow with discovered slugs
Adapting to updated tool schemas without hardcoding slugs
Running repeatable tasks in a persistent session with memory

Quick Start

Step 1: Verify RUBE_SEARCH_TOOLS and identify tool slugs for your use case
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["reply_io"] and ensure ACTIVE
Step 3: Run RUBE_MULTI_EXECUTE_TOOL with discovered tool_slug(s), proper arguments, memory, and session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Verify the connection status via RUBE_MANAGE_CONNECTIONS before execution
Use exact field names and types from the search results
Include memory in RUBE_MULTI_EXECUTE_TOOL calls (even if empty)
Reuse session IDs within a workflow and fetch new ones for separate workflows

Example Use Cases

Example: Discover tools for Reply IO, then execute a message-send tool using the returned slug
Example: Connect to the reply_io toolkit and run a scheduled status report
Example: Update an automation after RUBE_SEARCH_TOOLS reveals a new tool schema
Example: Reuse a session_id across multiple related Reply IO tasks
Example: Batch-run several tools with RUBE_REMOTE_WORKBENCH using run_composio_tool()

Frequently Asked Questions

Add this skill to your agents