How do I ensure tool schemas are current?

Always search tools first using RUBE_SEARCH_TOOLS and avoid hardcoding tool slugs.

What if the Nango connection is not ACTIVE?

Check with RUBE_MANAGE_CONNECTIONS; follow the returned auth link to activate, then recheck before running tools.

Is memory required in multi tool execution?

Yes, include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty to preserve state.

nango-automation

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

Files (1)

SKILL.md

2.8 KB

Nango Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/nango

Prerequisites

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

Step 2: Check Connection

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

Overview

Automates Nango operations through Composio's Nango toolkit using Rube MCP. It emphasizes always discovering current tool schemas with RUBE_SEARCH_TOOLS before running workflows, then manages connections and executes tools in sequence.

How This Skill Works

First, verify Rube MCP and RUBE_SEARCH_TOOLS are available to fetch current Nango tool schemas. Then use RUBE_MANAGE_CONNECTIONS to ensure the Nango toolkit is ACTIVE. Finally, run the discovered tool with RUBE_MULTI_EXECUTE_TOOL, passing in the required arguments, the session id, and a memory object.

When to Use It

Recurring Nango operations that require up to date tool schemas
Initial setup to discover available Nango tools and their input schemas
Before executing any workflow to confirm the Nango connection is ACTIVE
Bulk or batch Nango actions using RUBE_MULTI_EXECUTE_TOOL with multiple tool slugs
Workflows needing session continuity and handling paginated results from Nango

Quick Start

Step 1: Add RUBE MCP endpoint and confirm RUBE_SEARCH_TOOLS responds
Step 2: Discover available Nango tools with RUBE_SEARCH_TOOLS for your use case
Step 3: Check connection with RUBE_MANAGE_CONNECTIONS and then run a tool with RUBE_MULTI_EXECUTE_TOOL, including memory and session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE 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 for a single workflow and handle pagination tokens

Example Use Cases

Nightly CRM contact sync via Nango with latest schemas
Onboarding a new data source by establishing a Nango connection and triggering initial tasks
Bulk updates of multiple Nango tools after a schema refresh
Paginated Nango operations processed in sequential batches
Self-healing workflow that reactivates the connection and retries tools

Frequently Asked Questions

Add this skill to your agents