MCP Server Collector

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

python

19

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "chatmcp-mcp-server-collector": {
      "command": "uvx",
      "args": [
        "mcp-server-collector"
      ],
      "env": {
        "OPENAI_MODEL": "gpt-4o-mini",
        "OPENAI_API_KEY": "sk-xxx",
        "OPENAI_BASE_URL": "https://api.openai.com/v1",
        "MCP_SERVER_SUBMIT_URL": "https://mcp.so/api/submit-project"
      }
    }
  }
}

You run an MCP server designed to discover and collect MCP servers over the internet, enabling you to grow a distributed network of MCP-enabled services and share them through a centralized submission channel.

How to use

Retrieve MCP servers from a URL or from content you have, then submit any new MCP servers to the central directory. You can run the collector locally to discover servers and feed them into the directory, or operate the collector as a remote service that fetches and processes input for you. Use the collector together with an MCP client to expand your MCP ecosystem with minimal manual entry.

How to install

Prerequisites you need before installation:

Ensure you have the MCP runtime tool available in your environment (the collector is designed to run as a stdio-based service).
Have a method to run commands shown in the examples (for example, the UV tooling used to start the collector).

uvx
uv
npm
npx

# The collector can run under a standard stdio-based flow as shown in the deployment examples.

Additional configuration

Configure environment variables to enable AI-assisted submission and integration with the MCP directory.

OPENAI_API_KEY=YOUR_API_KEY
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_MODEL=gpt-4o-mini
MCP_SERVER_SUBMIT_URL=https://mcp.so/api/submit-project

Notes on runtime and tools

This server exposes three tools you can use to manage MCP server discovery and submission. Each tool is designed to be invoked with straightforward arguments from your MCP client or automation scripts.

- extract-mcp-servers-from-url: Extracts MCP Servers from given URL.  - Takes "url" as required string argument
- extract-mcp-servers-from-content: Extracts MCP Servers from given content.  - Takes "content" as required string argument
- submit-mcp-server: Submits a MCP Server to the MCP Server Directory like mcp.so.  - Takes "url" as required string argument and "avatar_url" as optional string argument

Troubleshooting tips

If you encounter debugging challenges, use the MCP Inspector for a detailed debugging session. Start the inspector with the command shown in the developer tooling, then access the provided URL in your browser to begin debugging.

Available tools

extract-mcp-servers-from-url

Extracts MCP Servers from a given URL. This tool fetches content from the provided URL and analyzes it to identify MCP server configurations.

extract-mcp-servers-from-content

Extracts MCP Servers from a block of content. This tool processes the supplied string and returns MCP server entries found within.

submit-mcp-server

Submits a discovered MCP server to the central MCP Server Directory. You provide the server URL and, optionally, an avatar URL for the entry.