mcpField
M
MCP Compass 🧭

MCP Compass 🧭

Local
github.com/liuyoshioDeveloper Tools248Updated 94w ago
Repository

About MCP Compass 🧭

MCP Compass is an MCP discovery and recommendation service that helps AI assistants find suitable MCP servers from natural language queries. It is aimed at users who want to locate available MCP services quickly. The project is released under the MIT license and can run via npx or from a local build.

Key features

  1. 01Searches MCP services using natural language queries
  2. 02Provides detailed metadata for each service
  3. 03Runs via npx or from a local build

Use cases

  1. 01Finding a suitable MCP server from a task description
  2. 02Enabling service discovery in Claude Desktop

MCP support

This is an MCP server that gives AI assistants the ability to discover and recommend MCP services.

#mcp-compass#mcp-discovery#service-recommendation

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "compass": {
      "command": "npx",
      "args": [
        "-y",
        "@liuyoshio/mcp-compass"
      ]
    }
  }
}
Run commandnpx -y @liuyoshio/mcp-compass

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@liuyoshio/mcp-compass

Tools

1

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
querystringYesDescription for the MCP Server needed. It should be specific and actionable, e.g.: GOOD: - 'MCP Server for AWS Lambda Python3.9 deployment' - 'MCP Server for United Airlines booking API' - 'MCP Server for Stripe refund webhook handling' BAD: - 'MCP Server for cloud' (too vague) - 'MCP Server for booking' (which booking system?) - 'MCP Server for payment' (which payment provider?) Query should explicitly specify: 1. Target platform/vendor (e.g. AWS, Stripe, MongoDB) 2. Exact operation/service (e.g. Lambda deployment, webhook handling) 3. Additional context if applicable (e.g. Python, refund events)

Details

From the project README

MCP Compass 🧭

Model Context Protocol

Compass MCP server

MCP Discovery & Recommendation

Experience MCP Compass 🌐

You can now experience MCP discovery directly on our website!
👉 Explore MCP Compass 👈

Dive in to discover the power of MCP services in action with real-time recommendations and insights.

What is this? 🤔

MCP Compass is a discovery & recommendation service that helps you explore Model Context Protocol servers. It acts as a smart guide that helps AI assistants find and understand available MCP services out there based on natural language queries, making it easier to discover and utilize the right tools for specific tasks.

Quick Example
MCP Compass Demo - Airtable Server Search

Features 🌟

  • 🔍 Smart Search: Find MCP services using natural language queries
  • 📚 Rich Metadata: Get detailed information about each service
  • 🔄 Real-time Updates: Always up-to-date with the latest MCP services MCP Servers
  • 🤝 Easy Integration: Simple to integrate with any MCP-compatible AI assistant

Quick Start 🚀

Usage
  1. Clone the repository

or

  1. Use npx
Installation

For Claude Desktop, edit your claude_desktop_config.json file:

MacOS/Linux
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows
code $env:AppData\Claude\claude_desktop_config.json

  1. As an MCP Service:

    Add to your AI assistant's MCP configuration to enable service discovery capabilities.

    {
"mcpServers": {
   "mcp-compass": {
      "command": "npx",
      "args": [
         "-y",
         "@liuyoshio/mcp-compass"
      ]
   }
}
}

    or

    {
"mcpServers": {
   "mcp-compass": {
      "command": "node",
      "args": [
         "/path/to/repo/build/index.js"
      ]
   }
}
}

License 📝

MIT License - See LICENSE file for details.

Support 💬

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.