Analyzer
MCP server for Python code analysis with RUFF linting and VULTURE dead code detection
What is Analyzer?
Analyzer is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for python code analysis with ruff linting and vulture dead code detection
MCP server for Python code analysis with RUFF linting and VULTURE dead code detection
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server for Python code analysis with RUFF linting and VU
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx analyzerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Analyzer
The Analyzer MCP Server integrates Python code quality tools directly into AI assistant workflows, exposing Ruff linting, Ruff formatting, type checking via ty, and Vulture dead code detection as MCP tools. It runs all analysis locally with no network calls or telemetry, making it safe for use with private codebases.
Prerequisites
- Python 3.10 or later with uv or pip installed
- uvx (recommended) or Docker as an alternative runtime
- An MCP-compatible client such as Claude Desktop, Claude Code, Cursor, VS Code, or Zed
- A Python project to analyze
Install the MCP server
Install mcp-server-analyzer using uvx (recommended for isolated execution) or pip.
# Recommended: uvx
uvx install mcp-server-analyzer
# Alternative: pip
pip install mcp-server-analyzer
# Docker
docker run ghcr.io/anselmoo/mcp-server-analyzer:latestAdd to Claude Desktop configuration
Register the analyzer server in your claude_desktop_config.json file. Using uvx ensures the server runs in an isolated environment.
Add to Claude Code (project-level)
For per-project setup in Claude Code, create a .mcp.json at the root of your Python project.
Configure for Zed or VS Code
For Zed, add the server under the 'context_servers' key in settings.json. For VS Code, add it to User Settings (JSON) or create a .vscode/mcp.json file.
Run your first analysis
Ask your AI assistant to analyze a Python file. The server will lint, format-check, type-check, and detect dead code, returning results without sending any data to external services.
Analyzer Examples
Client configuration
Add this to your claude_desktop_config.json to enable the Analyzer MCP server using uvx.
{
"mcpServers": {
"analyzer": {
"command": "uvx",
"args": ["mcp-server-analyzer"]
}
}
}Prompts to try
Use these prompts with Claude once the analyzer server is connected.
- "Run ruff-check on /path/to/my_module.py and fix all auto-fixable linting issues"
- "Scan /path/to/project/src for dead code using Vulture and list all unused functions"
- "Run a full combined analysis on /path/to/app.py covering linting, types, and dead code"
- "Check the type annotations in /path/to/models.py using ty"Troubleshooting Analyzer
uvx command not found
Install uv first by running 'curl -LsSf https://astral.sh/uv/install.sh | sh' on macOS/Linux or 'powershell -c irm https://astral.sh/uv/install.ps1 | iex' on Windows. Then restart your terminal so the PATH updates take effect.
ruff-check or vulture-scan returns no output for a file
Verify the file path passed to the tool is an absolute path. The server creates temporary files for analysis, so relative paths may not resolve correctly depending on the working directory. Also confirm the file contains valid Python syntax.
Server not visible after adding to config
Fully restart Claude Desktop or your MCP client after editing the config file. Config changes are not hot-reloaded. If using Claude Code, run 'claude mcp list' to verify the server appears in the registered servers list.
Frequently Asked Questions about Analyzer
What is Analyzer?
Analyzer is a Model Context Protocol (MCP) server that mcp server for python code analysis with ruff linting and vulture dead code detection It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Analyzer?
Follow the installation instructions on the Analyzer GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Analyzer?
Analyzer works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Analyzer free to use?
Yes, Analyzer is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Analyzer Alternatives — Similar Coding Agents Servers
Looking for alternatives to Analyzer? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Analyzer 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 Analyzer?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.