Makefile MCP Server
Exposes Makefile targets as callable tools for AI assistants.
makefilemcpserver
An MCP (Model Context Protocol) server that exposes Makefile targets as callable tools for AI assistants like Claude, Cursor, etc.
⚠️ ALPHA SOFTWARE - LOCAL USE ONLY ⚠️
This server executes Make commands with user-provided arguments. Only use in trusted environments. It intelligently parses out commands and args.
This almost certainly won't work flawlessly for your Makefile. In fact, it might not even work at all.
Installation
Prerequisites
- Node.js 16 or higher
makecommand available in PATH- A Makefile in your project directory
Quick Start
- Clone this repository:
git clone https://github.com/mparker3/makefilemcpserver.git
cd makefilemcpserver
- Install dependencies:
npm install
- Build the server:
npm run build
Usage
Add to your MCP server configuration:
{
"mcpServers": {
"makefilemcpserver": {
"command": "node",
"args": [
"/absolute/path/to/makefilemcpserver/build/index.js",
"/path/to/your/project"
]
}
}
}
The second argument (optional) specifies the directory containing your Makefile. If omitted, uses the current directory.
Example Makefile
# Build the project
build:
npm run build
# Run tests
test:
npm test
# Deploy to production
deploy: build test
./deploy.sh
This will expose tools: make_build, make_test, and make_deploy to Claude.
How It Works
- The server reads your Makefile at startup
- Each Make target becomes a tool with the name
make_<target> - Comments directly above targets become tool descriptions
- MCP clients can then run any target with optional arguments. We do some best-effort parsing of args from docs + commands, a better approach would just be to offload it to yet another LLM call(s) at startup.
Security Considerations
⚠️ WARNING: This server executes shell commands via Make. It currently has minimal input validation.
- Anything you expose in your Makefile, any MCP client will have access to. Highly recommend running locally only.
- The server does some de rigeur input sanitization, but no guarantees that an enterprising security researcher can't figure out a way around it.
Development
# Install dependencies
npm install
# Build once
npm run build
# Build and watch for changes
npm run watch
# Run the MCP Inspector for debugging
npm run inspector
Debugging
Since MCP servers communicate over stdio, use the MCP Inspector:
npm run inspector
Then open the provided URL to access debugging tools.
Contributing
This is alpha software. Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
License
MIT - See LICENSE file for details
Roadmap
- Support for multiple Makefiles
- Configuration for timeout values
- Better error messages and logging
- Tests and CI/CD pipeline
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
android-mcp-toolkit
A growing collection of MCP tools for Android Development. Currently features a deterministic Figma-SVG-to-Android-XML converter, with plans for Gradle analysis, Resource management, and ADB integration tools.
Supervisord MCP
A tool for managing Supervisord processes, integrated with AI agents via the Model Context Protocol (MCP). It offers standardized process control, real-time monitoring, and robust operations.
Remote MCP Server (Authless)
An example of a remote MCP server without authentication, deployable on Cloudflare Workers.
Maya MCP
MCP server for Autodesk Maya
Swap API
Free token swaps for AI agents. No API keys. Returns executable transaction calldata for 40+ EVM chains.
SynapseForge
A server for systematic AI experimentation and prompt A/B testing.
MCP Server Demonstration
A demonstration on setting up and using MCP servers within Cursor, with Docker examples.
MCP Ai server for Visual Studio
Visual Studio extension with 20 Roslyn-powered MCP tools for AI assistants. Semantic code navigation, symbol search, inheritance, call graphs, safe rename, build/test.
Unreal-Blender MCP
A unified server to control Blender and Unreal Engine via AI agents.
Tempo MCP Server
An MCP server for querying distributed tracing data from Grafana Tempo.