Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

code-index-mcp

MCP.Pizza Chef: johnhuang316

Code Index MCP is a Model Context Protocol server designed to enable large language models to index, search, and analyze code repositories efficiently. It recursively scans project directories to build searchable indexes, allowing real-time code navigation and pattern detection. This server facilitates deep codebase insights and integrates seamlessly with MCP to empower AI-driven development workflows with minimal setup.

Use This MCP server To

Index large code repositories for fast search and retrieval Search codebases for specific functions or patterns Analyze code structure and dependencies in real time Enable LLMs to navigate and understand complex projects Automate code review by extracting relevant code snippets Support multi-language code indexing and querying Integrate with developer tools for enhanced code exploration

README

Code Index MCP

MCP Server Python License

A Model Context Protocol server for code indexing, searching, and analysis.

What is Code Index MCP?

Code Index MCP is a specialized MCP server that provides intelligent code indexing and analysis capabilities. It enables Large Language Models to interact with your code repositories, offering real-time insights and navigation through complex codebases.

This server integrates with the Model Context Protocol (MCP), a standardized way for AI models to interact with external tools and data sources.

Key Features

  • Project Indexing: Recursively scans directories to build a searchable index of code files
  • Code Search: Find patterns, function definitions, and references across your codebase
  • File Analysis: Get detailed insights about file structure, imports, and complexity
  • Smart Filtering: Automatically ignores build directories, dependencies, and non-code files
  • Persistent Storage: Caches indexes for improved performance across sessions

Supported File Types

The server supports multiple programming languages and file extensions including:

  • Python (.py)
  • JavaScript/TypeScript (.js, .ts, .jsx, .tsx, .mjs, .cjs)
  • Frontend Frameworks (.vue, .svelte, .astro)
  • Java (.java)
  • C/C++ (.c, .cpp, .h, .hpp)
  • C# (.cs)
  • Go (.go)
  • Ruby (.rb)
  • PHP (.php)
  • Swift (.swift)
  • Kotlin (.kt)
  • Rust (.rs)
  • Scala (.scala)
  • Shell scripts (.sh, .bash)
  • Web files (.html, .css, .scss, .less, .sass, .stylus, .styl)
  • Template engines (.hbs, .handlebars, .ejs, .pug)
  • Database & SQL:
    • SQL files (.sql, .ddl, .dml)
    • Database-specific (.mysql, .postgresql, .psql, .sqlite, .mssql, .oracle, .ora, .db2)
    • Database objects (.proc, .procedure, .func, .function, .view, .trigger, .index)
    • Migration & tools (.migration, .seed, .fixture, .schema, .liquibase, .flyway)
    • NoSQL & modern (.cql, .cypher, .sparql, .gql)
  • Documentation/Config (.md, .mdx, .json, .xml, .yml, .yaml)

Installation

Prerequisites

  • Python 3.8 or higher
  • uv package manager (recommended)

Using uvx (recommended)

The easiest way to install and use code-index-mcp is with uvx:

uvx code-index-mcp

Using pip

Alternatively, you can install via pip:

pip install code-index-mcp

After installation, you can run it as a module:

python -m code_index_mcp

Integration with Claude Desktop

Add this to your Claude settings (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "code-index": {
      "command": "uvx",
      "args": [
        "code-index-mcp"
      ]
    }
  }
}

After adding the configuration, restart Claude Desktop and the Code Index MCP tools will be available.

Available Tools

Core Tools

  • set_project_path: Sets the base project path for indexing.
  • search_code: Searches for code matches within the indexed files.
  • find_files: Finds files in the project matching a given pattern.
  • get_file_summary: Gets a summary of a specific file, including line count, functions, imports, etc.
  • refresh_index: Refreshes the project index.
  • get_settings_info: Gets information about the project settings.

Utility Tools

  • create_temp_directory: Creates the temporary directory used for storing index data.
  • check_temp_directory: Checks the temporary directory used for storing index data.
  • clear_settings: Clears all settings and cached data.

Example Usage with Claude

Here are some examples of how to use Code Index MCP with Claude:

Setting a Project Path

Please set the project path to C:\Users\username\projects\my-python-project

Searching for Code Patterns

Search the code for all occurrences of "def process_data" in Python files

Getting a File Summary

Give me a summary of the main.py file in the project

Finding All Files of a Certain Type

Find all JavaScript files in the project

Development

Building from Source

  1. Clone the repository:
git clone https://github.com/username/code-index-mcp.git
cd code-index-mcp
  1. Install dependencies:
uv sync
  1. Run the server locally:
uv run code_index_mcp

Debugging

You can use the MCP inspector to debug the server:

npx @modelcontextprotocol/inspector uvx code-index-mcp

License

MIT License

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Languages

  • 繁體中文

code-index-mcp FAQ

How do I set up Code Index MCP server?
Install via Python 3.8+, configure the root directory to index, and start the server using provided commands.
Can Code Index MCP handle multiple programming languages?
Yes, it supports indexing and searching across various programming languages within the codebase.
How does Code Index MCP integrate with LLMs?
It exposes indexed code data through MCP, allowing LLMs like OpenAI, Claude, and Gemini to query and analyze code repositories.
Is real-time codebase updating supported?
Yes, it can update indexes incrementally as code changes, ensuring up-to-date search results.
What are the system requirements for running Code Index MCP?
Requires Python 3.8 or higher and sufficient disk space for indexing large repositories.
How secure is the Code Index MCP server?
It follows MCP principles for secure, scoped access, ensuring safe interaction between LLMs and code data.
Can I customize the indexing scope or patterns?
Yes, configuration options allow specifying directories, file types, and search patterns to tailor indexing.
Does Code Index MCP support integration with IDEs or other developer tools?
Yes, it can be integrated with IDEs and other tools to enhance code navigation and AI-assisted development.