Code Index MCP Server

@BangNGH

Basic information

About Code Index MCP Server

No overview available yet

Code Index MCP Server config

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

{
  "mcpServers": {
    "github-code-index-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "run.py"
      ]
    }
  }
}

Code Index MCP Server 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 Code Index MCP?

Code Index MCP is a Model Context Protocol server that enables large language models (LLMs) to index, search, and analyze code in project directories. It is intended for developers and AI assistants that need to navigate, search, and understand codebases.

How to use Code Index MCP?

Install Python 3.10+ and uv, clone the repository, then run uv run run.py. For Claude Desktop integration, add the server configuration to the Claude Desktop config file with the uv command and --directory pointing to the cloned folder. The first step is to set the project path via the LLM, after which you can search, analyze files, and navigate project structure.

Key features of Code Index MCP

Index and navigate project file structures
Search for specific patterns in code
Get detailed file summaries
Analyze code structure and complexity
Support for multiple programming languages
Persistent storage of project settings

Use cases of Code Index MCP

Quickly find all occurrences of a function or variable in a large codebase
Get a summary of all functions and classes in a specific file
Explore the directory structure of an unfamiliar project
Filter code search by file type (e.g., only Python or TypeScript files)

Frequently asked questions

What dependencies and runtime are required?

Python 3.10 or later and the uv package manager. All other dependencies are automatically handled by uv when running the server.

Where are index and settings data stored?

All data is stored in the `.code_indexer` folder inside the project directory, including config.json, file_index.pickle, and content_cache.pickle. This folder is gitignored to prevent committing indexing data.

Does the server support absolute paths or directory traversal?

No. Absolute path access is not allowed, and file path validation prevents directory traversal attacks. The project path must be explicitly set and has no default value.

What file types are supported for indexing and analysis?

The server supports Python, JavaScript/TypeScript, Java, C/C++, C#, Go, Ruby, PHP, Swift, Kotlin, Rust, Scala, Shell, HTML/CSS, Markdown, JSON, XML, and YAML files.

Can I use Code Index MCP with Claude Desktop?

Yes. Add the server configuration to Claude Desktop's config file with the `uv run run.py` command and the `--directory` option pointing to the correct project directory.

Comments

More Developer Tools MCP servers

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Eased

easedui

Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.

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

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

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools