Code2Flow

by kursk-ye

1 stars

455 downloads

Not rated

GitHub

About

Generates visual code flow diagrams from source code to help understand program structure, execution paths, and architectural relationships without manual diagramming.

Details

Author: kursk-ye
Repository: kursk-ye/code2flow-mcp-server
GitHub stars: 1
Downloads: 455
Categories: Productivity, Developer Tools, Design, Workplace, File Management, AI, API, Infrastructure, Knowledge Base, Other

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Code2Flow

Command (node, npx, python, etc.) python
Arguments
- Argument 1 path/to/server.py
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

JSON

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

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

JSON

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

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

JSON

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

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

JSON

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

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

JSON

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

JSON

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

From the repository

Install Python 3.7+, clone the repository, create a virtual environment, install dependencies (pip install -r requirements.txt), and install the code2flow CLI tool. Start the server with python server.py or use MCP tools like mcp dev server.py. You can also integrate it into Claude Desktop via mcp install server.py or into Cursor via a JSON configuration. The server exposes MCP tools such as generate_call_graph, check_code2flow_version, and analyze_code_complexity.

`generate_call_graph`

生成代码调用图。参数: source_paths (列表，必需), language (字符串，可选)

`check_code2flow_version`

检查 code2flow 版本。无参数

`analyze_code_complexity`

分析代码复杂度。参数: source_path (字符串，必需), language (字符串，可选)

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "code2flow": {
            "env": {},
            "args": [
                "path/to/server.py"
            ],
            "shell": true,
            "command": "python"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "path/to/server.py"
    ],
    "shell": true,
    "command": "python"
}

Macos

{
    "env": [],
    "args": [
        "path/to/server.py"
    ],
    "shell": true,
    "command": "python"
}

Windows

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

Code2Flow MCP 服务器

这是一个将 code2flow 命令行工具包装为 MCP (Model Context Protocol) 服务器的项目。它允许 AI 应用程序通过标准化的 MCP 协议生成和访问代码调用图。

功能特点

- 分析源代码并生成调用图
- 支持多种编程语言（Python、JavaScript、Ruby、PHP）
- 通过 MCP 协议提供服务，易于与 AI 应用集成
- 图像以 PNG 格式输出
- 提供版本检查和代码复杂度分析功能

安装要求

- Python 3.7+
- Windows 11 或其他支持的操作系统
- PowerShell 或其他命令行终端
- 已安装 code2flow 命令行工具

安装步骤

1. 克隆此仓库

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

cd code2flow-mcp-server

2. 创建并激活虚拟环境（推荐）

python -m venv venv

.\venv\Scripts\Activate.ps1  # 在 PowerShell 中

3. 安装依赖项

pip install -r requirements.txt

4. 安装 code2flow 命令行工具

pip install code2flow

使用方法

直接使用 Python 运行

1. 启动 MCP 服务器

python server.py

使用 MCP 工具运行

1. 使用 MCP Inspector 工具

mcp dev server.py

2. 安装到 Claude Desktop

mcp install server.py

3. 添加到 Cursor MCP 配置

"code2flow": {

  "command": "cmd",

  "args": [

    "/c",

    "python",

    "path/to/server.py"

  ]

}

可用工具

服务器提供以下 MCP 工具：

1. generate_call_graph - 生成代码调用图
2. check_code2flow_version - 检查 code2flow 版本
3. analyze_code_complexity - 分析代码复杂度

可用资源

服务器提供以下 MCP 资源：

1. help://code2flow - 帮助文档
2. languages://supported - 支持的语言列表
3. call-graph://图像ID - 生成的调用图图像

示例（使用 Python MCP 客户端）

import asyncio
from mcp.client import MCPClient
async def main():

    # 连接到服务器

    client = MCPClient("http://localhost:8000")

    

    # 创建新会话

    session = await client.create_session()

    

    # 调用工具生成调用图

    result = await session.call_tool("generate_call_graph", {

        "source_paths": ["path/to/your/code"],

        "language": "python"

    })

    

    # 获取资源 ID

    print(result)

    

    # 检查code2flow版本

    version_info = await session.call_tool("check_code2flow_version")

    print(version_info)

    

    # 分析代码复杂度

    complexity = await session.call_tool("analyze_code_complexity", {

        "source_path": "path/to/your/code",

        "language": "python"

    })

    print(complexity)
if __name__ == "__main__":

    asyncio.run(main())

配置选项

生成调用图时支持以下参数：

- source_paths：要分析的源代码文件或目录的路径列表
- output_path：（可选）输出文件的路径
- language：（可选）源代码语言（python、js、ruby、php）
- exclude：（可选）要排除的文件模式列表
- include：（可选）要包含的文件模式列表

文件结构

- server.py - 主服务器代码
- mcp_client_example.py - 客户端示例代码
- test_server.py - 测试代码
- requirements.txt - 依赖文件

许可证

MIT 29:["$","div",null,{"className":"my-8 pb-8 h-full max-w-5xl mx-auto","children":["$","div",null,{"className":"grid grid-cols-1 md:grid-cols-3 gap-6","children":["$","$L30",null,{"mcp":{"id":"mcp_qA7imQqcXVIb","name":"Code2Flow","description":"Generates visual code flow diagrams from source code to help understand program structure, execution paths, and architectural relationships without manual diagramming.","logo":"https://avatars.githubusercontent.com/kursk-ye","banner_url":null,"stars":1,"downloads":0,"categories":["productivity","dev","design","workplace","file","ai","cli","api","infrastructure","documentation"],"isRecommended":false,"created_at":"2025-04-17T01:24:47.001436+00:00","updated_at":"2025-04-17T01:50:33.016459+00:00","author":"kursk-ye","average_rating":0,"total_ratings":0,"github_url":"https://github.com/kursk-ye/code2flow-mcp-server","commit":"main","official":fa

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

generate_call_graph

check_code2flow_version

analyze_code_complexity

Claude Desktop / Cursor

Linux

Macos

Windows

Code2Flow MCP 服务器

功能特点

安装要求

安装步骤

使用方法

直接使用 Python 运行

使用 MCP 工具运行

可用工具

可用资源

示例（使用 Python MCP 客户端）

配置选项

文件结构

许可证

Install

More like this

Time

Sentry

Github

Git

GitLab

Context 7

`generate_call_graph`

`check_code2flow_version`

`analyze_code_complexity`