Happy slice of mcp pizzaMCP.pizza

code-index-mcp

MCP.Pizza Chef: johnhuang316

This server builds a searchable index of a project folder, so a chat assistant can locate a function, trace where it is called, or describe a file without you pasting anything in. Ten languages get deep parsing and fifty-plus other file types get lighter handling. A file watcher keeps the list current as you edit, and the index is cached for speed. No account or key is required — you add a few lines of configuration, then name the folder you want read.

Coding

Use This MCP server To

Find every place an old function is still used Search a project for anything touching login or passwords Get a tour of an unfamiliar project's main parts Locate the file that produces a specific error message Review a file's structure before I start changing it

README

Code Index MCP

MCP Server Python License Sponsor

Intelligent code indexing and analysis for Large Language Models

Transform how AI understands your codebase with advanced search, analysis, and navigation capabilities.

code-index-mcp MCP server

Overview

Code Index MCP is a Model Context Protocol server that bridges the gap between AI models and complex codebases. It provides intelligent indexing, advanced search capabilities, and detailed code analysis to help AI assistants understand and navigate your projects effectively.

Perfect for: Code review, refactoring, documentation generation, debugging assistance, and architectural analysis.

Quick Start

🚀 Recommended Setup (Most Users)

The easiest way to get started with any MCP-compatible application:

Prerequisites: Python 3.10+ and uv

code-index-mcp FAQ

Which apps does this work with?
Anything that supports MCP, including Claude Desktop, Claude Code, and the Codex CLI; the readme gives a config example for each.
Do I need an API key?
No. It reads files on your own computer and needs no account.
Can I use this to understand a project I just downloaded?
Yes — point it at the folder, ask for the main components, then drill into whichever file looks interesting.
How hard is setup?
You paste a few lines into your app's configuration. Python 3.10 or newer and the uv tool need to be installed first.
Does it send my code anywhere?
The indexing happens on your machine; only what the assistant actually reads back goes to the model you are already using.
Does it notice when I edit files?
Yes, a watcher keeps the file list current, though refreshing the detailed symbol information takes a deeper rebuild.