How do you ensure current schemas?

Always call RUBE_SEARCH_TOOLS first to fetch up-to-date tool slugs, input schemas, recommended execution plans, and known pitfalls.

What if the connection isn't ACTIVE?

Use RUBE_MANAGE_CONNECTIONS with toolkit agenty to authenticate; ensure status ACTIVE before executing.

No API keys required; add the MCP endpoint only as described.

agenty-automation

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

Files (1)

SKILL.md

2.8 KB

Agenty Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/agenty

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Agenty operations through Composio's Agenty toolkit via Rube MCP. Prerequisites include a connected Rube MCP with RUBE_SEARCH_TOOLS available and an active Agenty connection using the agenty toolkit. Always search tool schemas first to fetch current inputs and prevent hardcoding slugs.

How This Skill Works

Using the Core Workflow Pattern, first discover available tools with RUBE_SEARCH_TOOLS for your Agenty use case. Then confirm the Agenty connection is ACTIVE with RUBE_MANAGE_CONNECTIONS, and finally execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL using the discovered tool_slug and schema-compliant arguments.

When to Use It

When starting a new Agenty workflow, discover current tool schemas before selecting tools.
When you need to verify that the Agenty connection is ACTIVE prior to execution.
When executing a discovered tool, ensure you pass memory and session_id as required.
When refreshing tool capabilities, always run RUBE_SEARCH_TOOLS instead of hardcoding slugs.
When orchestrating multiple tools in a session, reuse session_id and manage pagination as needed.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration (no API keys needed).
Step 2: Run RUBE_SEARCH_TOOLS to discover available Agenty tool slugs and schemas for your use case.
Step 3: Run RUBE_MANAGE_CONNECTIONS to ensure the agenty toolkit is ACTIVE, then execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and a memory object.

Best Practices

Always run RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.
Check RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
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 generate new ones for new workflows; monitor pagination tokens.

Example Use Cases

Automate a nightly Agenty ingestion task by discovering tools, authenticating, and executing a selected slug with appropriate arguments.
Orchestrate a sequence of Agenty operations for data processing using a shared session.
Validate updated tool schemas after a RUBE_SEARCH_TOOLS run and adjust workflows accordingly.
Handle a multi-tool run that fetches pagination tokens and continues until completion.
Troubleshoot tool execution by confirming ACTIVE connection and including memory in multi-execute calls.

Frequently Asked Questions

Add this skill to your agents