%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Tearags MCP
TeaRAGs is a semantic code search MCP server designed for coding agents. It supports large - scale codebases through AST - aware chunking and incremental indexing, and uses Git trajectories (such as 19 signals including code changes, author information, and defect repair rates) for intelligent re - ranking, surpassing traditional embedding similarity retrieval.
rating : 2.5 points
downloads : 6.3K
What is TeaRAGs?
TeaRAGs is an intelligent assistant specifically designed for code search. Different from traditional code search tools, it can not only understand the semantic meaning of code but also analyze the evolution history of code. This means that when you search for code, it can not only find code with similar functions but also tell you which code is more stable, which authors are more familiar with the relevant field, and which code has a lower risk of modification.How to use TeaRAGs?
TeaRAGs is integrated and used through AI assistants such as Claude. First, configure the server, and then issue search instructions through the AI assistant. You can let the AI assistant index the entire codebase and then ask questions like 'Find the code for handling user authentication' or 'Show the API endpoints that have been modified frequently recently'. The system will automatically analyze the code semantics and evolution history and return the most relevant results.Applicable scenarios
1. When new developers are getting familiar with the codebase, quickly find relevant code examples. 2. When refactoring code, identify stable and reliable code templates. 3. When fixing bugs, find solutions to similar problems. 4. During code review, understand the historical modification situation of the code. 5. When assessing technical debt, identify high - risk code areas.Main features
Evolution trajectory analysis
Analyze the git history of the code, track 19 evolution signals such as the modification frequency of each function, author changes, and bug repair records to help understand the stability and reliability of the code.
Intelligent semantic search
Search based on the semantic meaning of the code, and can understand the actual functions of functions, classes, and variables, rather than just keyword matching.
AST intelligent chunking
Use the abstract syntax tree (AST) to intelligently split the code into meaningful blocks (such as functions and classes) to ensure the integrity of the search results.
Intelligent result re - ranking
Provide a variety of preset re - ranking strategies: hotspots, code ownership, tech debt, security audit, etc., to optimize the results according to different scenarios.
Multi - model support
Support local models (Ollama) and cloud models (OpenAI, Cohere, Voyage), and users can flexibly choose according to their needs.
Incremental indexing
Support incremental updates of large - scale codebases, only index the changed parts, and improve efficiency.
Advantages
Intelligently understand the code evolution history and provide more reliable search results
Support local deployment to protect code privacy and security
Seamlessly integrate with mainstream AI assistants (Claude) for easy use
Open - source and free, with customizable and extensible functions
Strong ability to handle large - scale codebases, supporting millions of lines of code
Limitations
Requires configuration and deployment, which has a certain threshold for non - technical users
It takes a long time to index a large codebase for the first time
Relies on git history data, and the effect is limited for newly created projects
Requires a certain amount of computing resources (CPU/memory)
Currently mainly supports common programming languages
How to use
Environment preparation
Install the necessary software: Node.js, Docker/Podman, Git. Ensure that the system has enough memory and storage space.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%230080ff;%20}%20%3c/style%3e%3c/defs%3e%3cpath%20class='st0'%20d='M16.2,11.1c.4.5.4,1.2,0,1.8l-4.7,7.1h-3.8l5.3-8L7.6,4h3.8l4.7,7.1Z'/%3e%3c/svg%3e)
Download and install
Clone the project repository and install the dependency packages.
Start the service
Use Docker Compose to start the necessary database and model services.
Configure the AI assistant
Add the TeaRAGs server to AI assistants such as Claude Code.
Start using
Send instructions through the AI assistant to index and search for code.
Usage examples
Case 1: New developers getting familiar with the codebase
New developers joining the team need to quickly understand the implementation of the user authentication module.
Case 2: Refactoring technical debt
The team needs to identify and refactor high - risk code areas.
Case 3: Code review assistance
Understand the historical background of the code being reviewed during code review.
Case 4: Looking for code templates
Need to implement a new REST API endpoint and look for existing best practices as a reference.
Frequently Asked Questions
What's the difference between TeaRAGs and ordinary code search tools?
Do I need programming experience to use it?
Which programming languages are supported?
Is my code data safe?
How long does it take to index a large codebase?
Can I use it for projects without git history?
Related resources
Full documentation
Detailed installation guide, configuration instructions, advanced functions, and usage tips
GitHub repository
Source code, issue feedback, contribution guidelines
Quick start guide
15 - minute quick start guide
Architecture design
System architecture and technical implementation details
Community discussion
User discussions, experience sharing, and function suggestions
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
24.4K
4.3 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
20.4K
4.5 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
35.3K
5 points
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.5K
4.3 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#
31.1K
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
64.4K
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
21.0K
4.5 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
96.8K
4.7 points