Skip to main content
Glama
codemenu-mcp

codemenu-mcp

by Extiri

codemenu-mcp

MCP server for CodeMenu snippet manager.

Overview

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.

Related MCP server: smart-coding-mcp

Features

The server exposes the following tools for interacting with 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

Prerequisites

  • CodeMenu must be running on your Mac (Learn more)

  • API must be enabled in CodeMenu settings (CodeMenu → Settings → API)

  • Node.js >= 18.0.0

CodeMenu API Setup

  1. Open CodeMenu

  2. Go to Settings → API

  3. Enable the API server

  4. Note the port (default: 1300)

  5. Optionally, set an API key for authentication

The CodeMenu API runs locally at http://127.0.0.1:1300/v1 by default.

Installation

From npm (when published)

npm install -g git+https://github.com/Extiri/codemenu-mcp.git

From source

git clone https://github.com/Extiri/codemenu-mcp.git
cd codemenu-mcp
npm install
npm link

Configuration

The server connects to the local CodeMenu API and supports the following environment variables:

Environment Variables

  • CODEMENU_API_URL - The base URL for the CodeMenu API (default: http://127.0.0.1:1300/v1)

  • CODEMENU_API_KEY - Your CodeMenu API key

Example Configuration for Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "codemenu": {
      "command": "node",
      "args": ["/path/to/codemenu-mcp/index.js"],
      "env": {
        "CODEMENU_API_URL": "http://127.0.0.1:1300/v1",
        "CODEMENU_API_KEY": "your-api-key"
      }
    }
  }
}

Or if installed globally via npm:

{
  "mcpServers": {
    "codemenu": {
      "command": "codemenu-mcp",
      "env": {
        "CODEMENU_API_KEY": "your-api-key"
      }
    }
  }
}

Note: If you didn't enable API key protection in CodeMenu settings, you can omit the CODEMENU_API_KEY environment variable.

Usage

Once configured, the server will be automatically started by your MCP client (e.g., Claude Desktop). The AI assistant will have access to your CodeMenu snippets and can:

  • Browse and search through your code snippets

  • Find snippets by language, tags, or groups

  • Retrieve specific snippets with full code content when needed

  • List available tags and groups for better organization

Example Interactions

Searching snippets:

"Search my CodeMenu snippets for sorting algorithms"

Listing snippets by language:

"Show me all my JavaScript snippets from CodeMenu"

Getting a specific snippet:

"Show me the full code for snippet ID ABC123"

Listing tags:

"What tags do I have in CodeMenu?"

Development

Running the Server

npm start

The server communicates over stdio, which is the standard transport for MCP servers.

Testing

npm test

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

Project Structure

  • index.js - Main server implementation

  • package.json - Project metadata and dependencies

  • test.js - MCP protocol test suite

  • README.md - This file

  • LICENSE - MIT license

  • .gitignore - Files to exclude from git

API Reference

The server implements the Model Context Protocol and exposes tools that correspond to CodeMenu API endpoints:

  • GET /snippets - List snippets with optional filters (query, language, tag, group)

  • GET /tags - List all tags

  • GET /groups - List all groups

For detailed information about the CodeMenu API, refer to the CodeMenu API documentation.

Requirements

  • Node.js >= 18.0.0

  • CodeMenu application with API enabled

  • MCP client (e.g., Claude Desktop)

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

For issues related to:

Troubleshooting

Server can't connect to CodeMenu:

  • Ensure CodeMenu application is running

  • Check that API is enabled in CodeMenu settings

  • Verify the port matches your configuration (default: 1300)

  • If you enabled API key protection, ensure CODEMENU_API_KEY is set correctly

No snippets returned:

  • Verify you have snippets in CodeMenu

  • Check that your search filters aren't too restrictive

  • Try listing without filters first

Authentication errors:

  • Check if the CODEMENU_API_KEY environment variable is set properly

Available Tools

4 tools
get_snippetA

Get full details of a specific snippet by ID, including the complete code content

Inputs: id (required).

list_groupsB

List all groups available in CodeMenu

Inputs: no named parameters.

list_snippetsA

List code snippets from CodeMenu without full code content (to reduce token usage). Returns id, title, description, language, abbreviation, tags, and group info.

Inputs: tag, group, query, language.

list_tagsB

List all tags available in CodeMenu

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a unique resource or action: get_snippet retrieves full content by ID, list_snippets returns metadata only, list_tags enumerates tags, and list_groups enumerates groups. There is no overlap in purpose, so an agent can easily select the right tool.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern with clear prefixes: get_ for single-item retrieval and list_ for collection enumeration. The naming is predictable and uniform across the set.

    Tool Count4/5

    Four tools is a compact set that covers reading and browsing snippets, tags, and groups. It is slightly under-scoped for a snippet manager because it omits search/filter or mutation tools, but each existing tool earns its place.

    Completeness3/5

    The read surface is partially complete: list_snippets and get_snippet cover snippet retrieval, and list_tags/list_groups expose metadata. However, there is no create, update, or delete for snippets, and no way to search or filter snippets by tag or group, which are notable gaps for a snippet management domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to perform intelligent semantic code search across codebases using local AI embeddings for meaning-based retrieval.
      6
      24 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic code search and AI-powered chat for local codebases, with support for multiple AI providers and a plugin system.
      12 npm
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI coding assistants to discover, inspect, and run API requests in Bruno collections locally, keeping all data private.
      3
      40 npm
      MIT