nrwl

Nx MCP Server

Community nrwl
Updated

Nx Console is the user interface for Nx & Lerna.

Nx MCP Server

npm version

A Model Context Protocol server implementation for Nx.

Overview

The Nx MCP server gives LLMs deep access to your monorepo’s structure: project relationships, file mappings, runnable tasks, ownership info, tech stacks, Nx generators, and even Nx documentation. With this context, LLMs can generate code tailored to your stack, understand the impact of a change, and apply modifications across connected files with precision. This is possible because Nx already understands the higher-level architecture of your workspace, and monorepos bring all relevant projects into one place.

Read more in our blog post and in our docs.

Installation and Usage

There are two ways to use this MCP server:

a) Run it via the nx-mcp package

Simply invoke the MCP server via npx or your package manager's equivalent.

Here's an example of a mcp.json configuration:

{
  "servers": {
    "nx-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["nx-mcp@latest", "/path/to/your/workspace"]
    }
  }
}

For VSCode you can also run:

code --add-mcp '{"name":"nx-mcp","command":"npx","args":["nx-mcp", "/path/to/your/workspace"]}'

Refer to your AI tool's documentation for how to register an MCP server. For example, Cursor or Claude Desktop support MCP.

If you want to host the server instead of communicating via stdio, you can use the --sse and --port flags. Keep in mind that the Nx MCP server only supports a single concurrent connection right now, so connecting multiple clients at the same time might break in some cases.

Run nx-mcp --help to see what options are available.

b) Use the Nx Console extension

If you're using Cursor you can directly install the Nx Console extension which automatically manages the MCP server for you.

More info:

Available Tools

Currently, the Nx MCP server provides a set of tools. Resources, Roots and Prompts aren't supported yet.

  • nx_workspace: Returns an annotated representation of the local nx configuration and the project graph
  • nx_project_details: Returns the full project configuration for a specific nx project
  • nx_docs: Retrieves documentation sections relevant to user queries
  • nx_generators: Returns a list of available generators in the workspace
  • nx_generator_schema: Provides detailed schema information for a specific generator
  • nx_available_plugins: Returns a list of available Nx plugins from the npm registry with their descriptions

When no workspace path is specified, only the nx_docs and nx_available_plugins tools will be available.

Contributing & Development

Contributions are welcome! Please see the Nx Console contribution guide for more details.

The basic steps are:

  1. Clone the Nx Console repository and follow installation steps
  2. Build the nx-mcp using nx run nx-mcp:build (or nx run nx-mcp:build:debug for debugging with source maps)
  3. Use the MCP Inspector to test out your changes

License

MIT

MCP Server · Populars

MCP Server · New

    tradesdontlie

    TradingView MCP Bridge

    AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation

    Community tradesdontlie
    us

    fastCRW — Open Source Web Scraping API for AI Agents

    Fast, lightweight Firecrawl alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/v1/scrape, /v1/crawl, /v1/search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

    Community us
    capsulerun

    Capsule MCP Server

    Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

    Community capsulerun
    capsulerun

    Capsule

    Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

    Community capsulerun
    Kohei-Wada

    Taskdog

    Terminal task manager with intelligent schedule optimization.Keyboard-only. No dragging, no micromanagement.

    Community Kohei-Wada