Code2flow MCP Server

🚀 Code2Flow MCP Server

This project wraps the code2flow command-line tool into an MCP (Model Context Protocol) server. It enables AI applications to generate and access code call graphs through the standardized MCP protocol.

🚀 Quick Start

The Code2Flow MCP Server allows AI applications to generate and access code call graphs via the MCP protocol. Here's how to get started:

✨ Features

• Analyze source code and generate call graphs.
• Support multiple programming languages (Python, JavaScript, Ruby, PHP).
• Provide services via the MCP protocol, making it easy to integrate with AI applications.
• Output images in PNG format.
• Offer version checking and code complexity analysis functions.

📦 Installation

Requirements

• Python 3.7+
• Windows 11 or other supported operating systems
• PowerShell or other command-line terminals
• The code2flow command-line tool installed

Steps

1. Clone this repository:

git clone https://github.com/kursk-ye/code2flow-mcp-server.git
cd code2flow-mcp-server

2. Create and activate a virtual environment (recommended):

python -m venv venv
.\venv\Scripts\Activate.ps1  # In PowerShell

3. Install dependencies:

pip install -r requirements.txt

4. Install the code2flow command-line tool:

pip install code2flow

💻 Usage Examples

Run directly with Python

1. Start the MCP server:

python server.py

Run with MCP tools

1. Use the MCP Inspector tool:

mcp dev server.py

2. Install it to Claude Desktop:

mcp install server.py

3. Add it to the Cursor MCP configuration:

"code2flow": {
  "command": "cmd",
  "args": [
    "/c",
    "python",
    "path/to/server.py"
  ]
}

Example (Using the Python MCP client)

import asyncio
from mcp.client import MCPClient

async def main():
    # Connect to the server
    client = MCPClient("http://localhost:8000")
    
    # Create a new session
    session = await client.create_session()
    
    # Call the tool to generate a call graph
    result = await session.call_tool("generate_call_graph", {
        "source_paths": ["path/to/your/code"],
        "language": "python"
    })
    
    # Get the resource ID
    print(result)
    
    # Check the code2flow version
    version_result = await session.call_tool("check_code2flow_version")
    print(version_result)
    
    # Analyze code complexity
    complexity_result = await session.call_tool("analyze_code_complexity", {
        "source_paths": ["path/to/your/code"]
    })
    print(complexity_result)

if __name__ == "__main__":
    asyncio.run(main())

📚 Documentation

Available Tools

The server provides the following MCP tools:

1. generate_call_graph - Generate a code call graph.
2. check_code2flow_version - Check the code2flow version.
3. analyze_code_complexity - Analyze code complexity.

Available Resources

The server provides the following MCP resources:

1. help://code2flow - Help documentation.
2. languages://supported - List of supported languages.
3. call-graph://image ID - Generated call graph images.

Configuration Options

The server can be configured using the following command-line arguments when starting:

• --port or -p: Specify the port the service listens on (default: 8000).
• --debug or -d: Enable debug mode.

For example:

python server.py --port 8080 --debug

File Structure

The project directory structure is as follows:

code2flow-mcp-server/
├── server.py          # Main server file
├── requirements.txt   # List of dependencies
└── README.md          # Project documentation

📄 License

This project is licensed under the MIT License.