How do I start using piggy-automation with Rube MCP?

Add the MCP endpoint, verify connectivity with RUBE_SEARCH_TOOLS, establish a Piggy connection with RUBE_MANAGE_CONNECTIONS, then discover tools and execute with RUBE_MULTI_EXECUTE_TOOL.

Do I need to re-discover tool schemas on every run?

Yes. Tool schemas can change, so re-running RUBE_SEARCH_TOOLS ensures you use current tool slugs and input fields.

What if the Piggy connection isn’t ACTIVE?

Follow the auth link returned by RUBE_MANAGE_CONNECTIONS to complete setup, then re-check until the status shows ACTIVE before running workflows.

piggy-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Piggy Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/piggy

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Piggy operations through Composio's Piggy toolkit using Rube MCP. Always search for current tool schemas first, ensure an ACTIVE Piggy connection, and execute tools with memory-aware payloads.

How This Skill Works

You verify connectivity with RUBE_SEARCH_TOOLS to discover Piggy tools, then establish or confirm a Piggy connection via RUBE_MANAGE_CONNECTIONS. When ready, execute a chosen tool with RUBE_MULTI_EXECUTE_TOOL, supplying exact input fields from the discovery results and a memory payload, while reusing sessions when appropriate.

When to Use It

When starting a new Piggy workflow and you need the latest tool schemas
When wiring a Piggy task and you must confirm the connection is ACTIVE before execution
When discovering available Piggy tools and their input schemas prior to running
When performing bulk Piggy operations in a single session using multi-tool execution
When building multi-step Piggy workflows that reuse a session across steps

Quick Start

Step 1: Add the Rube MCP endpoint (https://rube.app/mcp) and verify connectivity with RUBE_SEARCH_TOOLS
Step 2: Connect to Piggy using RUBE_MANAGE_CONNECTIONS and ensure the status is ACTIVE (follow auth if needed)
Step 3: Discover tools and execute one with RUBE_MULTI_EXECUTE_TOOL using the discovered tool_slug, required arguments, memory, and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS before running any tool to get current schemas
Check RUBE_MANAGE_CONNECTIONS status is ACTIVE before execution
Use exact field names and types from the tool discovery results
Include memory (even if empty) in RUBE_MULTI_EXECUTE_TOOL payloads
Reuse session IDs where appropriate and manage new sessions for separate workflows

Example Use Cases

Automate a Piggy task by discovering tools with RUBE_SEARCH_TOOLS, connecting to Piggy via RUBE_MANAGE_CONNECTIONS, then executing a single tool with RUBE_MULTI_EXECUTE_TOOL using the discovered schema
Bulk Piggy operations: use RUBE_REMOTE_WORKBENCH to run multiple tools via run_composio_tool(), providing per-tool memory payloads
Recurring Piggy workflow: reuse a session_id across daily runs to optimize setup and state retention
Handle schema changes: re-discover tools before each run and adapt tool_slug/arguments to new schemas
Pagination handling: fetch all tools using RUBE_SEARCH_TOOLS and iterate until no tokens remain

Frequently Asked Questions

Add this skill to your agents