Meta MCP Server

Your command deck for MCP servers. MCP Deck is an intelligent MCP (Model Context Protocol) router: it spawns your child MCP servers, embeds their

Local serverstdioPython

What is the Meta MCP MCP server?

Meta MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Your command deck for MCP servers. MCP Deck is an intelligent MCP (Model Context Protocol) router: it spawns your child MCP servers, embeds their tools, and exposes them to an MCP client through a single connection — either proxying every.

What the assistant can call

Once Meta MCP is connected, these are the calls the assistant has available:

  • serve — Run the MCP server over stdio for Claude Desktop/Code (see above)
  • start — Dashboard/full-stack mode with auto-setup + web UI (default command)
  • run — Start the server without auto-setup or config auto-detection
  • list-strategies — List available tool-selection strategies
  • debug-vector — Run a test query against the vector search index
  • regenerate-embeddings — Recompute tool embeddings (--force to clear and rebuild)
  • init-config — Write a default mcpdeck.yaml
  • health — Check system health and dependencies

Setting it up

The server ships on PyPI as mcpdeck, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration and credentials

  • Python 3.11+ - uv — provides the uvx and uv commands used throughout this README. If you only have pipx, run pipx install uv to get uvx. - Docker or Apple Container (macOS Apple Silicon) — needed to run Qdrant, which backs vector-based tool selection. Optional if you only ever

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Meta MCP's toolset — serve, start, run and 5 more — is a fair guide to whether it matches your workflow. It is maintained by anirudhlath; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the meta mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
serveRun the MCP server over stdio for Claude Desktop/Code (see above)
startDashboard/full-stack mode with auto-setup + web UI (default command)
runStart the server without auto-setup or config auto-detection
list-strategiesList available tool-selection strategies
debug-vectorRun a test query against the vector search index
regenerate-embeddingsRecompute tool embeddings (--force to clear and rebuild)
init-configWrite a default mcpdeck.yaml
healthCheck system health and dependencies

How to install the Meta MCP MCP server

{
  "mcpServers": {
    "mcpdeck": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/anirudhlath/mcpdeck",
        "mcpdeck",
        "serve",
        "--mcp-servers-json",
        "/absolute/path/to/mcp-servers.json"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.11+ - uv — provides the uvx and uv commands used throughout this README. If you only have pipx, run pipx install uv to get uvx. - Docker or Apple Container (macOS Apple Silicon) — needed to run Qdrant, which backs vector-based tool selection. Optional if you only ever

Example prompts to try

  • Use Meta MCP to serve.
  • Use Meta MCP to start.
  • Use Meta MCP to run.

Frequently asked questions

It connects Meta MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (serve, start, run, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Meta MCP directly.