curl2mcp

Turn any curl command into a Model Context Protocol tool server in seconds.

🎯 Why?

MCP adoption is exploding, but connecting a random REST endpoint still means writing a server, schema, and request glue. curl is the universal language for HTTP requests, yet there is no tiny zero-config adapter that converts a curl command into an MCP tool. curl2mcp fills that gap by parsing {placeholders} and serving the request over stdio.

Target audience: AI tool builders, Claude/Cursor users, platform engineers, and agent developers who need to expose HTTP APIs to MCP clients without writing boilerplate.

Related MCP server: cli-wrap-mcp

✨ Features

• ✨ Parse a curl command into an MCP tool schema with placeholder extraction

• ✨ Run the templated request directly from the CLI for quick testing

• ✨ Serve the tool over MCP stdio for Claude, Cursor, or any MCP client

• ✨ Zero external runtime dependencies beyond the Python standard library

🚀 Quick Start

# Install
pip install curl2mcp

# Run
curl2mcp --help

📦 Installation

From Source

git clone https://github.com/YOUR_USERNAME/curl2mcp.git
cd curl2mcp

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest -v

🎬 Demo

The GIF above was recorded using Charm VHS:

vhs < demo.tape

📖 Usage

# Show help
curl2mcp --help

# Common usage examples
curl2mcp --example

🏗️ Architecture

graph LR
    A[Input] --> B[Core Engine]
    B --> C[Output]
    B --> D[Plugins]
    D --> E[Extensions]

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repo

2. Create a feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add amazing feature')

4. Push to the branch (git push origin feature/amazing-feature)

5. Open a Pull Request

📄 License

MIT © 2026 — See LICENSE for details.

If this project helped you, please ⭐ star it!

Made with ❤️ and AI