Advertise
MCP.so
Sign In
M

MCP Code Analyzer

@mszewczy

Repository

Basic information

Category

Developer Tools

Transports

stdio

Author

mszewczy

Submitted by

Marek Szewczyk

About MCP Code Analyzer

A Model Context Protocol (MCP) server implementation for comprehensive code analysis. This tool integrates with Claude Desktop to provide code analysis capabilities through natural language interactions.

#mcp#code#analyzer

MCP Code Analyzer config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "code-analyzer": {
      "command": "python",
      "args": [
        "-m",
        "mcp_code_analyzer",
        "--analyze-paths",
        "C:\\Projects\\path1"
      ]
    }
  }
}

MCP Code Analyzer tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Code Analyzer?

MCP Code Analyzer is a code analysis and management tool that integrates with Claude Desktop. It analyzes code at both project and file levels, providing insights for needed changes and ensuring related usages are updated when modifications are made.

How to use MCP Code Analyzer?

Install via pip install -e . after cloning the repository. Configure Claude Desktop by editing %AppData%\Claude\claude_desktop_config.json to point to your project paths using the --analyze-paths argument. Additional paths or files can be analyzed via chat messages.

Key features of MCP Code Analyzer

  • Project structure analysis in XML tree format
  • Project statistics and technology analysis
  • File and import analysis
  • Reference finding across the codebase
  • File operations with automatic version control backups
  • Line-by-line code modification (currently has issues)

Use cases of MCP Code Analyzer

  • Automatically updating all references when renaming or moving a function
  • Understanding project architecture and dependencies before making changes
  • Detecting unused imports or files across a codebase
  • Backing up and safely modifying code with version control support

Frequently asked questions

1

What are the system requirements?

Python 3.10 or later and Windows (Linux/macOS support not yet tested).

2

Does MCP Code Analyzer modify or delete files?

Yes. The tool performs file operations that can modify or delete files. Always backup your codebase before using any modification features.

3

What working tools are available?

Project analysis tools (analyze_project_structure, analyze_project_statistics, analyze_project_technology), code analysis tools (analyze_imports, analyze_file, find_references), file operations (file_operations, version_control), and code_modifier (with known big issues).

4

Are there known limitations?

Chat context limitations may interrupt large file modifications. AI-generated documentation comments can affect code operation. Some tools are still in testing phase and may not work as expected.

5

Can I analyze multiple project paths?

Yes. Multiple project paths can be specified in the Claude Desktop configuration, and additional paths or files can be analyzed via chat messages with no limit on the number.

Comments

More Developer Tools MCP servers

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

1

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

1

Nebelus

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

1
Advertise