How do I ensure tool slugs are current?

Always call RUBE_SEARCH_TOOLS before executing any Ngrok task; don't hardcode slugs or argument names.

What if the Ngrok connection shows not ACTIVE?

Run RUBE_MANAGE_CONNECTIONS for the ngrok toolkit and follow the returned auth link until status is ACTIVE before running tools.

Do I need to include a memory object in tool calls?

Yes. Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty, to satisfy the schema.

ngrok-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Ngrok Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/ngrok

Prerequisites

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

Step 2: Check Connection

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

Overview

Automates Ngrok operations through Composio's Ngrok toolkit using Rube MCP. It emphasizes discovering current tool schemas before execution to adapt to changes and avoid broken workflows.

How This Skill Works

Connect to Rube MCP, verify Ngrok connectivity, and discover available tools with RUBE_SEARCH_TOOLS. Then execute a chosen tool via RUBE_MULTI_EXECUTE_TOOL, passing the correct schema fields and a memory payload, reusing sessions where appropriate.

When to Use It

You need to discover current Ngrok tool slugs and schemas before scripting.
You must verify and establish an ACTIVE Rube MCP connection for ngrok.
You want to execute a discovered tool with the correct schema and arguments.
You plan to run multiple Ngrok operations in a single workflow.
You need to fetch updated tool schemas after changes to avoid failures.

Quick Start

Step 1: Add the Rube MCP endpoint and verify RUBE_SEARCH_TOOLS responds.
Step 2: Connect to Ngrok with RUBE_MANAGE_CONNECTIONS and ensure ACTIVE.
Step 3: Discover tools with RUBE_SEARCH_TOOLS and execute a tool with RUBE_MULTI_EXECUTE_TOOL, including memory and session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to get fresh tool 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 and handle pagination when listing tools.

Example Use Cases

Automate tunnel creation and status checks using discovered tools.
Update tunnel config after a schema change without hardcoding slugs.
Run multiple Ngrok operations in one workflow with RUBE_MULTI_EXECUTE_TOOL.
Reconnect after token expiry by following the auth link and rechecking ACTIVE.
Troubleshoot failures by re-discovering tool schemas with RUBE_SEARCH_TOOLS.

Frequently Asked Questions

Add this skill to your agents