Code Index MCP
An MCP server based on Zoekt for fast search and indexing of local source code, supporting cross-platform and rich query syntax.
rating : 2 points
downloads : 6.1K
What is Code Index MCP Server?
Code Index MCP Server is a tool specifically designed for code search. It can build a code index on your local computer, enabling AI assistants (such as Claude) to quickly search and analyze your source code. It uses advanced indexing technology to achieve millisecond-level search responses even in large-scale codebases.How to use Code Index MCP Server?
First, install the server program, and then configure it to your AI tool (such as Claude Desktop). Next, index your code directory. After that, you can ask code-related questions to the AI assistant in natural language, and the AI will use this server to search your codebase and return accurate results.Use cases
Suitable for developers to find specific functions, understand code structures, find API usages, locate relevant code when debugging problems, or find all places using a certain pattern during refactoring in large projects. It is especially suitable for quickly understanding others' code during team collaboration.Main Features
Lightning-fast search
Using Zoekt's trigram indexing technology, it can achieve sub-second search responses even in millions of lines of code, supporting regular expressions and complex queries.
Multi-directory index management
You can create indexes for multiple project directories separately. Each index is stored independently, supporting directory-specific or global searches.
Powerful query language
Supports advanced search functions such as file type filtering, programming language filtering, and boolean operators, making searches more precise.
Intelligent filtering
Automatically skips non-source code directories such as node_modules and vendor, as well as non-text files such as binary files and images, improving search efficiency.
Cross-platform support
Supports macOS (Intel and Apple Silicon) and Linux systems, meeting the needs of different development environments.
Concise output format
Search results are displayed in a compact grep-style format, minimizing context usage and improving AI processing efficiency.
Advantages
Extremely fast search speed, especially suitable for large codebases
Runs completely locally, and code data never leaves your computer
Seamlessly integrates with AI assistants, allowing code search in natural language
Supports complex search patterns and regular expressions
Automatically filters out irrelevant files, resulting in cleaner search results
Limitations
Requires pre-building an index, and you need to wait for the indexing to complete on first use
Currently does not support the Windows system
Indexes occupy a certain amount of disk space
Needs to be manually configured in AI tools
How to Use
Download and Install
Download the corresponding pre-compiled version according to your operating system, or install it using the Go tool.
Configure to Claude Desktop
Add the server configuration to the Claude Desktop configuration file.
Index Your Code Directory
Index your project directory through the AI assistant or the command line.
Start Searching Code
Now you can let the AI assistant search your code in natural language.
Usage Examples
Find a specific function definition
When you need to find the definition location of a specific function, you can use a simple text search.
Search by file type
When you only want to search in files of a specific type, you can use the file filter.
Exclude test files
When you only want to search for production code and exclude test files.
Multi-condition combined search
When you need a complex search that meets multiple conditions simultaneously.
Frequently Asked Questions
How much disk space does the index occupy?
How long does indexing take?
Is my code data secure?
Which programming languages are supported?
How to update the index?
Can multiple projects be indexed simultaneously?
Related Resources
GitHub Repository
Source code, issue tracking, and the latest version
MCP Registry
Page in the official MCP registry
Zoekt Project
The underlying search indexing engine used
MCP Protocol Documentation
Official specification of the Model Context Protocol

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
20.3K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
61.8K
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
31.7K
5 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.7K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
27.2K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
50.6K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
40.7K
4.8 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
78.7K
4.7 points
