MCP Connector

Explore MCP Services with Natural Language

MCP Compass is a discovery and recommendation service for Model Context Protocol servers, enabling AI assistants to find and use tools via natural language.

Maintainer of this project? Claim this page to edit the listing.


86
Spark score
out of 100
Updated Jan 2025
Version 1.0.0
Models
universal

Add to Favorites

Why it matters

Discover and understand available Model Context Protocol (MCP) services. This asset acts as an intelligent guide, allowing you to explore MCP servers using natural language queries and retrieve rich, real-time information about each service.

Outcomes

What it gets done

01

Search MCP services using natural language queries.

02

Retrieve detailed metadata for MCP services.

03

Get real-time updates on the latest MCP services.

04

Integrate with AI assistants compatible with MCP.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-mcp-compass | bash

Overview

MCP Compass MCP Server

MCP Compass is a discovery and recommendation service for Model Context Protocol (MCP) servers. It helps AI assistants find and understand available MCP services using natural language queries. MCP Compass can be integrated with MCP-compatible AI assistants by adding it to their MCP configuration. This allows the AI assistant to discover and utilize MCP services.

What it does

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 based on natural language queries, making it easier to discover and utilize the right tools for specific tasks.

To integrate MCP Compass with an MCP-compatible AI assistant, you can add it to your AI assistant's MCP configuration. For example, using npx:

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

Alternatively, you can configure it to run a local Node.js script:

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

MCP Compass ๐Ÿงญ

Model Context Protocol

Compass MCP server

MCP Discovery & Recommendation

Experience MCP Compass ๐ŸŒ

You can now experience MCP discovery directly on our website!
๐Ÿ‘‰ Explore MCP Compass ๐Ÿ‘ˆ

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


What is this? ๐Ÿค”

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 ๐ŸŒŸ

  • ๐Ÿ” Smart Search: Find MCP services using natural language queries
  • ๐Ÿ“š Rich Metadata: Get detailed information about each service
  • ๐Ÿ”„ Real-time Updates: Always up-to-date with the latest MCP services MCP Servers
  • ๐Ÿค Easy Integration: Simple to integrate with any MCP-compatible AI assistant

Quick Start ๐Ÿš€

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"
          ]
       }
    }
    }
    

FAQ

Common questions

Discussion

Questions & comments ยท 0

Sign In Sign in to leave a comment.