Complexipy MCP Server
Analyzes cognitive complexity of Python code by scanning files and directories to identify functions exceeding complexity thresholds using the complexipy library.
README
Complexipy MCP Server
A Model Context Protocol (MCP) server that wraps complexipy to provide cognitive complexity analysis for Python codebases. This server uses the complexipy Python API for accurate and robust analysis.
Features
- Directory Scanning: Recursively analyze all
.pyfiles in a directory and filter by complexity threshold. - File Scanning: Analyze a single Python file.
- Data Processing: Uses
pandasfor efficient data filtering and sorting. - Clean Output: Returns JSON formatted results (list of objects).
- No Emojis: Pure data output suitable for machine consumption.
- Stdio Transport: Uses standard input/output for communication, making it compatible with most MCP clients.
Installation & Usage
Quick Start
You can run the server directly using uvx (no installation required):
uvx complexipy-mcp
Configuration for Claude Desktop
Add the following configuration to your MCP client settings (e.g., claude_desktop_config.json):
{
"mcpServers": {
"complexipy": {
"command": "uvx",
"args": [
"complexipy-mcp"
]
}
}
}
Local Development
- Clone the repository.
- Install dependencies:
uv sync - Run the server locally:
uv run complexipy-mcp
Local Configuration for Claude Desktop
If you are developing locally, point the configuration to your local setup:
{
"mcpServers": {
"complexipy": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/complexipy-mcp",
"run",
"complexipy-mcp"
]
}
}
}
Tools
scan_directory
Scans a directory for files exceeding a cognitive complexity threshold.
- Arguments:
directory_path(string): Absolute path to the directory to scan.threshold(integer): Complexity limit (default: 15).
- Returns: JSON string containing a list of files that exceed the threshold.
[ { "file_path": "/abs/path/to/file.py", "complexity": 25, "functions": [ { "name": "function_name", "complexity": 10, "line_start": 5, "line_end": 15 } ], "status": "exceeds_threshold" } ]
scan_file
Scans a single file for cognitive complexity.
- Arguments:
file_path(string): Absolute path to the file.threshold(integer): Complexity limit (default: 15).
- Returns: JSON string containing the result if it exceeds the threshold.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。