Zoekt MCP
The Zoekt MCP Server is a Model Context Protocol service based on the Zoekt code search engine, providing code search, repository discovery, and content fetching functions, specifically designed for AI tool integration.
rating : 2.5 points
downloads : 6.7K
What is the Zoekt MCP Server?
The Zoekt MCP Server is a code search service specifically designed for AI assistants. It provides an interface through the Model Context Protocol (MCP), enabling AI tools to efficiently search and understand the content in code repositories. This service is built on the Zoekt search engine, which is the code indexing engine used by Sourcegraph.How to use the Zoekt MCP Server?
Before use, you need to configure the Zoekt search server, and then start the MCP service through simple installation steps. After the service is started, AI tools can access the search function through the HTTP interface or integrate through the dedicated MCP protocol.Applicable scenarios
It is particularly suitable for scenarios such as AI assistants that need to understand large code repositories, code auto - completion tools, and technical documentation generation systems. Developers and technical teams can also use it to build custom code search and analysis tools.Main features
Code search
Use Zoekt's trigram indexing technology to achieve fast code search, supporting simultaneous search across multiple code repositories.
Advanced query language
Supports advanced search functions such as regular expressions, file filters, language filters, and boolean operators.
Repository discovery
You can find code repositories by name and browse their directory structures.
Content fetching
It can fetch the content of specific files in the repository or list the directory structure.
AI integration
Specifically designed for large language models (LLMs), providing search prompt guidance functions to help AI build more effective queries.
Advantages
High - performance code indexing based on Zoekt, with fast search speed
Supports complex search query syntax for precise code lookup
Optimized for AI tools, providing search guidance functions
Multiple installation methods, supporting Docker containerized deployment
Lightweight service with low resource consumption
Limitations
Requires pre - configuration of the Zoekt search server
Does not support real - time index updates (depending on Zoekt configuration)
Initial indexing of large code repositories may take a long time
Advanced search functions require learning the query syntax
How to use
Install dependencies
Ensure that Python 3.10+ and the Zoekt search server are installed.
Choose an installation method
You can install it using UV (recommended), pip, or Docker.
Configure environment variables
You must set ZOEKT_API_URL to point to your Zoekt instance.
Start the service
Select the corresponding start command according to the installation method.
Integrate into AI tools
If using the Cursor editor, add the server configuration to.mcp.json.
Usage examples
Find test cases
The AI assistant needs to find all test functions in the project to understand the test coverage.
Understand API usage
The AI assistant needs to understand the usage of a certain API in the project.
Code pattern analysis
Developers want to analyze the usage of a certain design pattern in the project.
Frequently Asked Questions
What is the difference between the Zoekt MCP Server and using Zoekt directly?
How do I know if my Zoekt server is working properly?
What could be the reason for incomplete search results?
Which code repositories are supported for search?
How to update the content of the indexed repository?
Related resources
Zoekt official documentation
Official documentation and installation guide for the Zoekt search engine
Model Context Protocol specification
Official specification document for the MCP protocol
Example configuration repository
Contains configuration examples for various usage scenarios
Installation video tutorial
Complete video guide for installation and configuration from scratch

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
14.8K
4.5 points

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
16.7K
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
45.0K
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
23.8K
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#
20.3K
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
45.0K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
15.0K
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
29.5K
4.8 points
