respond-io-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/respond-io-automation --openclawRespond IO Automation via Rube MCP
Automate Respond IO operations through Composio's Respond IO toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/respond_io
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Respond IO connection via
RUBE_MANAGE_CONNECTIONSwith toolkitrespond_io - Always call
RUBE_SEARCH_TOOLSfirst 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_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitrespond_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: "Respond 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 Respond IO task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["respond_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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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 Respond IO-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit respond_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/respond-io-automation/SKILL.mdView on GitHub Overview
Automates Respond IO tasks via Composio's Rube MCP. Always discover current tool schemas first and verify an ACTIVE Respond IO connection before running workflows.
How This Skill Works
Discover available Respond IO tools with RUBE_SEARCH_TOOLS to obtain input schemas. Then verify the connection using RUBE_MANAGE_CONNECTIONS and proceed only if the status is ACTIVE. Finally, execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL, providing a memory payload and the current session_id.
When to Use It
- Automate an end-to-end Respond IO workflow via MCP
- When tool schemas change, re-discover tools before execution
- While establishing or renewing Respond IO connections
- When running multiple Respond IO actions within a single session
- When discovering tools with potential pagination and repeated fetches
Quick Start
- Step 1: Ensure RUBE MCP is configured (https://rube.app/mcp) and RUBE_SEARCH_TOOLS responds; connect with RUBE_MANAGE_CONNECTIONS for the respond_io toolkit
- Step 2: Run RUBE_SEARCH_TOOLS to discover available tools and their input schemas for your use case
- Step 3: Execute a selected tool with RUBE_MULTI_EXECUTE_TOOL, including memory and the session_id
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing any workflow to get current schemas
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before running tools
- Do not hardcode tool slugs or argument names; use exact fields from the discovery results
- Always include a memory object in RUBE_MULTI_EXECUTE_TOOL calls (even if empty)
- Reuse session IDs within a workflow and handle pagination tokens to fetch all results
Example Use Cases
- Discover tools for a Respond IO use case and run a tool to create a ticket in Respond IO
- Update ticket status in Respond IO using a discovered tool slug and payload
- After a tool schema change, re-run RUBE_SEARCH_TOOLS and adapt your workflow
- Run multiple Respond IO actions in a single session to optimize latency
- Perform bulk Respond IO operations using RUBE_REMOTE_WORKBENCH and run_composio_tool()