Codemenu MCP Server

If you already use Codemenu MCP, the codemenu mcp mcp server is the piece that lets your assistant work with it directly. MCP server for CodeMenu snippet manager.

What the server does

This is a Model Context Protocol (MCP) server that provides integration with the CodeMenu local HTTP API, allowing AI assistants to access and search through code snippets stored in CodeMenu.

• list_snippets — - List snippets without full code content (to reduce token usage). Returns id, title, description, language, abbreviation, tags, and group info. Supports filtering by query, language, tag, or group
• get_snippet — - Retrieve the full details of a specific snippet by ID, including complete code content
• list_tags — - List all available tags in CodeMenu
• list_groups — - List all available groups in CodeMenu

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

• Testing — This validates that the server correctly implements the MCP protocol. To test actual API calls, make sure CodeMenu is running with the API enabled

Installation

git on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Credentials and setup notes

Configuration is passed through the environment: CODEMENU_API_URL, CODEMENU_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

• CodeMenu must be running on your Mac (Learn more) - API must be enabled in CodeMenu settings (CodeMenu → Settings → API) - Node.js >= 18.0.0

Where it fits

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. Codemenu MCP's toolset — Testing — is a fair guide to whether it matches your workflow. It is maintained by extiri; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

• 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.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.