Code Checker
MCP server providing code quality checks (pylint and pytest) with smart LLM-friendly prompts for analysis and fixes. Enables Claude and other AI assistants to analyze your code and suggest improvements.
What is Code Checker?
Code Checker is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server providing code quality checks (pylint and pytest) with smart llm-friendly prompts for analysis and fixes. enables claude and other ai assistants to analyze your code and suggest improvement...
MCP server providing code quality checks (pylint and pytest) with smart LLM-friendly prompts for analysis and fixes. Enables Claude and other AI assistants to analyze your code and suggest improvements.
This server falls under the Developer Tools and Coding Agents categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server providing code quality checks (pylint and pytest)
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-code-checkerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Code Checker
MCP Code Checker (mcp-tools-py) is a Python MCP server that runs pylint, pytest, and mypy on your local Python projects and returns results formatted as structured, LLM-friendly output. Claude and other AI assistants connected to this server can analyze code quality, run your test suite, and perform type checking, then immediately suggest fixes based on the actual tool output. It is aimed at Python developers who want their AI coding assistant to have real-time, ground-truth insight into code quality rather than relying on inference alone.
Prerequisites
- Python 3.9 or later
- pylint, pytest, and mypy installed in the Python environment the server will use for analysis
- The mcp-tools-py package installed from GitHub
- Claude Desktop or another MCP-compatible AI client
Install mcp-tools-py from GitHub
Install the package directly from the GitHub repository. This makes the mcp-tools-py command available.
pip install git+https://github.com/MarcusJellinghaus/mcp-tools-py.gitEnsure analysis tools are installed in the target environment
The server needs pylint, pytest, and mypy accessible via the Python interpreter it uses. Install them in the same virtual environment as mcp-tools-py.
pip install pylint pytest mypyTest the server from the command line
Run the server pointing at your project directory to confirm it starts correctly. The --project-dir argument is required.
mcp-tools-py --project-dir /path/to/your/projectAdd the server to Claude Desktop config
Register the server in claude_desktop_config.json. Specify the --project-dir pointing to the root of the Python project you want to analyze.
{
"mcpServers": {
"mcp-code-checker": {
"command": "mcp-tools-py",
"args": ["--project-dir", "/path/to/your/project"]
}
}
}Optionally configure a separate venv for the analysis tools
If your project uses a different Python environment than where mcp-tools-py is installed, use --venv-path to point the server at the environment where pylint, pytest, and mypy live.
mcp-tools-py --project-dir /path/to/project --venv-path /path/to/project/.venvCode Checker Examples
Client configuration
Claude Desktop configuration for mcp-code-checker targeting a specific Python project directory.
{
"mcpServers": {
"mcp-code-checker": {
"command": "mcp-tools-py",
"args": [
"--project-dir", "/Users/you/myproject",
"--venv-path", "/Users/you/myproject/.venv",
"--log-level", "INFO"
]
}
}
}Prompts to try
Example prompts for running code quality checks through Claude once the server is configured.
- "Run pylint on the src/ directory and tell me which files have the most issues."
- "Execute the pytest suite and summarize any failing tests with their error messages."
- "Run mypy with strict mode on my project and list all type errors by file."
- "Check the code quality of auth.py with pylint and suggest specific fixes for each warning."
- "Run pylint targeting only the 'error' and 'warning' categories and generate a report."Troubleshooting Code Checker
run_pylint_check returns 'pylint not found' or similar error
Ensure pylint is installed in the Python environment the server is using. If using --venv-path, verify that the virtual environment at that path has pylint installed: run '/path/to/.venv/bin/pip list | grep pylint'.
pytest runner skips tests or reports 'no tests found'
The --project-dir must point to the root of your project where pytest.ini, pyproject.toml, or setup.cfg configures test discovery. Verify pytest finds tests by running 'pytest --collect-only' manually from the project directory.
mcp-tools-py command not found after installation
The package installs the CLI entry point via pip. Ensure the Python environment's bin directory is on your PATH. If using a virtual environment, activate it first or specify the full path to the binary in the Claude Desktop config.
Frequently Asked Questions about Code Checker
What is Code Checker?
Code Checker is a Model Context Protocol (MCP) server that mcp server providing code quality checks (pylint and pytest) with smart llm-friendly prompts for analysis and fixes. enables claude and other ai assistants to analyze your code and suggest improvements. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Code Checker?
Follow the installation instructions on the Code Checker GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Code Checker?
Code Checker works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Code Checker free to use?
Yes, Code Checker is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Code Checker Alternatives — Similar Developer Tools Servers
Looking for alternatives to Code Checker? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Code Checker in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Code Checker?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.