code2flow-mcp-server

# Code2Flow MCP Server This is a project that wraps the code2flow command-line tool as an MCP (Model Context Protocol) server. It allows AI applications to generate and access code call graphs through the standardized MCP protocol. ## Features - Analyzes source code and generates call graphs - Supports multiple programming languages (Python, JavaScript, Ruby, PHP) - Provides services via the MCP protocol, making it easy to integrate with AI applications - Outputs images in PNG format - Offers version checking and code complexity analysis features ## Installation Requirements - Python 3.7+ - Windows 11 or other supported operating systems - PowerShell or other command-line terminals - The code2flow command-line tool must be installed ## Installation 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 ### 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 to Claude Desktop ``` mcp install server.py ``` 3. Add to Cursor MCP configuration ```json "code2flow": { "command": "cmd", "args": [ "/c", "python", "path/to/server.py" ] } ``` ## Available Tools The server provides the following MCP tools: 1. `generate_call_graph` - Generates a code call graph 2. `check_code2flow_version` - Checks the code2flow version 3. `analyze_code_complexity` - Analyzes 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://imageID` - Generated call graph image ### Example (Using Python MCP Client) ```python 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 resource ID print(result) # Check code2flow version version_info = await session.call_tool("check_code2flow_version") print(version_info) # Analyze code complexity complexity = await session.call_tool("analyze_code_complexity", { "source_path": "path/to/your/code", "language": "python" }) print(complexity) if __name__ == "__main__": asyncio.run(main()) ``` ## Configuration Options The following parameters are supported when generating a call graph: - `source_paths`: A list of paths to the source code files or directories to analyze - `output_path`: (optional) The path for the output file - `language`: (optional) The source code language (python, js, ruby, php) - `exclude`: (optional) A list of file patterns to exclude - `include`: (optional) A list of file patterns to include ## File Structure - `server.py` - Main server code - `mcp_client_example.py` - Client example code - `test_server.py` - Test code - `requirements.txt` - Dependency file ## License MIT