Discover and Configure MCP Servers Automatically

1 MCP Server 🚀

MCP of MCPs - automatically discover and configure MCP servers on your machine (remote or local).

After setup, you can usually just say:

“I want to perform . Call the deep_search tool and follow the outlined steps.”

The goal is that you only install this MCP server, and it handles the rest (searching servers, selecting servers, configuring servers, etc.).

Demo video 🎥: https://youtu.be/W4EAmaTTb2A

Quick Setup

Choose one of the following:

1. Remote (simplest & fastest ⚡💨)
2. Local (prebuilt) - Docker, uvx, or npx
3. Local (from source) - run this repo directly

1) Remote 🌍⚡💨

Use the hosted endpoint (recommended for the simplest setup).

Docs + guided setup: https://mcp.1mcpserver.com/

Configure your MCP client

Add the following entry to your client config file:

• Cursor: ./.cursor/mcp.json
• Gemini CLI: ./gemini/settings.json (see Gemini docs)
• Claude Desktop:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
• Codex:
  • macOS: ~/.codex/config.toml
  • Windows: %USERPROFILE%\.codex\config.toml

Remote config (JSON):

{
  "mcpServers": {
    "1mcpserver": {
      "url": "https://mcp.1mcpserver.com/mcp/",
      "headers": {
        "Accept": "text/event-stream",
        "Cache-Control": "no-cache"
      }
    }
  }
}

If you already have other servers configured, just merge this entry under mcpServers For example:

{
  "mcpServers": {
    "1mcpserver": {
      "url": "https://mcp.1mcpserver.com/mcp/",
      "headers": {
        "Accept": "text/event-stream",
        "Cache-Control": "no-cache"
      }
    },
    "file-system": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
    }
  }
}

Tip: If your client supports it, move the config file into your home directory to apply globally.

2) Local (prebuilt) 💻

Use this when you want everything local, or when your MCP client only supports STDIO.

2A) Docker 🐳

 docker run -p 8080:8080 ghcr.io/particlefuture/1mcpserver:latest

Running on other host ports:

 docker run -p <FREE_HOST_PORT_NUM>:8080 ghcr.io/particlefuture/1mcpserver:latest

Running with stdio instead of streamable-http (You might see some delays when trying to connect):

run --rm -i ghcr.io/particlefuture/1mcpserver:latest --local

{
  "mcpServers": {
    "1mcpserver": {
      "url": "https://mcp.1mcpserver.com/mcp/"
    }
  }
}

2B) npx 📦

npx -y @1mcpserver/1mcpserver

3) Local (from source) 🧩

Clone this repo and run directly.

git clone https://github.com/particlefuture/MCPDiscovery.git
cd MCPDiscovery
uv sync
uv run server.py --local

{
  "mcpServers": {
    "1mcpserver": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "<PATH_TO_CLONED_REPO>",
        "run",
        "server.py",
        "--local"
      ]
    }
  }
}

If your client supports remote url servers, you can use the Remote setup instead.

Optional: grant file-system access 📁

If you want your LLM to have file-system access, add an MCP filesystem server and point it at the directory you want to allow:

{
  "mcpServers": {
    "file-system": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "~/"]
    }
  }
}

Architecture 🧠

There are two search modes:

Quick Search ⚡

For explicit requests like: “I want an MCP server that handles payments.”

Returns a shortlist of relevant MCP servers.

Deep Search 🌊

For higher-level or complex goals like: “Build a website that analyzes other websites.”

The LLM breaks the goal into components/steps, finds MCP servers for each part, and if something is missing, it asks whether to:

• ignore that part,
• break it down further, or
• implement it ourselves.

Deep Search stages:

1. Planning - identify servers, keys, and config changes
2. Testing - verify servers (via test_server_template_code)
3. Acting - execute the workflow using the configured servers

Change Log 🕒

• July 31 2025: Upgrade to 0.2.0. Added agentic planning.
• Dec 12 2025: Support for Gemini + Codex
• Dec 13 2025: Easier local setup with docker and npm.

Future 🔮

• Better demo videos (new domain, narrated walkthrough)
• Model Context Communication Protocol (MCCP): standard server-to-server messaging
• Avoid calling tools with an internal_ prefix unless instructed
• Improve MCP server database schema: server, description, url, config json, extra setup (docker/api key/etc)

Troubleshooting 🧰

• If using a venv and you get ModuleNotFoundError even after installing: delete the venv and recreate it.

Please create an issue or directly contact me zjia71@gatech.edu if you encounter ANY issue of frustration. I really hope the setup is as smooth as possible!!

Star History