MCP HubMCP Hub
chatmcp

mcp-server-collector

by: chatmcp

A MCP Server used to collect MCP Servers over the internet.

18created 08/12/2024
Visit
monitoring
network

📌Overview

Purpose: The MCP Server aims to facilitate the collection of MCP Servers over the internet, streamlining access to these resources.

Overview: The MCP Server Collector is a specialized tool designed to extract and submit MCP Server data from various sources online. This utility leverages integrations with external APIs to enhance its functionality, enabling seamless data retrieval and submission processes.

Key Features:

  • Extract MCP Servers from URL: This tool allows users to input a URL to extract relevant MCP Server information directly from the specified web address, simplifying data collection.

  • Extract MCP Servers from Content: Users can provide raw content to receive extracted MCP Server details, making it convenient to obtain information from non-URL sources.

  • Submit MCP Server: This feature enables users to submit extracted MCP Server information to a central directory, such as mcp.so, providing broad visibility and access to the collected data. It requires a URL and optionally an avatar URL for submission.

mcp-server-collector MCP server

A MCP Server used to collect MCP Servers over the internet.

Components

Resources

No resources yet.

Prompts

No prompts yet.

Tools

The server implements 3 tools:

  • extract-mcp-servers-from-url: Extracts MCP Servers from a given URL.

    • Takes "url" as a required string argument.

  • extract-mcp-servers-from-content: Extracts MCP Servers from given content.

    • Takes "content" as a required string argument.

  • submit-mcp-server: Submits an MCP Server to the MCP Server Directory like mcp.so.

    • Takes "url" as a required string argument and "avatar_url" as an optional string argument.

Configuration

A .env file is required to be set up with the following variables:

OPENAI_API_KEY="sk-xxx"
OPENAI_BASE_URL="https://api.openai.com/v1"
OPENAI_MODEL="gpt-4o-mini"

MCP_SERVER_SUBMIT_URL="https://mcp.so/api/submit-project"

Quickstart

Install

Claude Desktop

  • On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • On Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Servers Configuration
"mcpServers": {
  "fetch": {
    "command": "uvx",
    "args": ["mcp-server-fetch"]
  },
  "mcp-server-collector": {
    "command": "uv",
    "args": [
      "--directory",
      "path-to/mcp-server-collector",
      "run",
      "mcp-server-collector"
    ],
    "env": {
      "OPENAI_API_KEY": "sk-xxx",
      "OPENAI_BASE_URL": "https://api.openai.com/v1",
      "OPENAI_MODEL": "gpt-4o-mini",
      "MCP_SERVER_SUBMIT_URL": "https://mcp.so/api/submit-project"
    }
  }
}
Published Servers Configuration
"mcpServers": {
  "fetch": {
    "command": "uvx",
    "args": ["mcp-server-fetch"]
  },
  "mcp-server-collector": {
    "command": "uvx",
    "args": [
      "mcp-server-collector"
    ],
    "env": {
      "OPENAI_API_KEY": "sk-xxx",
      "OPENAI_BASE_URL": "https://api.openai.com/v1",
      "OPENAI_MODEL": "gpt-4o-mini",
      "MCP_SERVER_SUBMIT_URL": "https://mcp.so/api/submit-project"
    }
  }
}

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:

    uv sync

  2. Build package distributions:

    uv build

    This will create source and wheel distributions in the dist/ directory.

  3. Publish to PyPI:

    uv publish

Note: Set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN
  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory path-to/mcp-server-collector run mcp-server-collector

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Community

About the author