Matter AI
Provides advanced code review, implementation planning, and pull request generation using Matter AI.
Matter AI MCP Server
MatterAI MCP offers code reviews right in your IDE when using AI Agents such as in Cursor, Windsurf, VS Code, Cline and more to enhances your development workflow. Built with FastMCP in Python, it provides advanced code review capabilities, implementation planning, and pull request generation to help you release code with confidence.
Features
- Code review tools - Get comprehensive code reviews for individual files or full git diffs
- Implementation planning - Generate detailed implementation plans for AI agents
- Pull request generation - Create pull requests with auto-generated titles and descriptions
- Random cat facts - Because who doesn't love cat facts?
Requirements
- Python 3.11+
- See
requirements.txtfor dependencies
Installation
pip install -r requirements.txt
Setup
API Key
To use Matter AI MCP Server, you need an API key:
- Obtain your API key from https://app.matterai.dev/settings
- Use this key in your MCP configuration as shown below
MCP Configuration
Create an MCP configuration file with the following content:
{
"mcpServers": {
"matter-ai": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.matterai.so/sse",
"--header",
"X-AUTH-TOKEN:MATTER_AI_API_KEY"
]
}
}
}
Replace MATTER_AI_API_KEY with your actual API key.
Usage
Run the server:
python server.py
The server will start on http://localhost:9000 (default for FastMCP).
Connecting from Cursor or Windsurf
- Use the MCP (Model Context Protocol) integration
- Point to:
http://localhost:9000/sse - Tools will auto-discover and appear in the client
Tools
1. Code Review
codereview(generated_code: str, git_owner: str, git_repo: str, git_branch: str, git_user: str, languages: str) -> str
Provides code review for the generated code.
2. Full Code Review
codereview_full(git_diff: str, git_owner: str, git_repo: str, git_branch: str, git_user: str) -> str
Provides a comprehensive code review based on git diff output.
1. Cat Fact
cat_fact() -> str
Returns a random cat fact.
Docker Build and Use
Building the Docker Image
docker build -t matter-ai-mcp .
Running the Docker Container
docker run -p 9000:9000 -e MATTER_API_ENDPOINT=https://api.matterai.so
The server will be accessible at http://localhost:9000.
License
MIT
Resources:
- Website: https://matterai.so
- Docs: https://docs.matterai.so
Servidores relacionados
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Gateway MCP Server
A gateway server that intelligently routes MCP requests to multiple backend servers.
Azure DevOps MCP Server
An MCP server for Azure DevOps, enabling AI assistants to interact with Azure DevOps APIs.
Mong MCP Server
A moby-like random name generator for use with tools like Claude Desktop and VS Code Copilot Agent.
RenPy MCP
MCP server + visual development tools for Ren'Py visual novel engine. 60 tools, story map, live dashboard, standalone CLI.
prolog-reasoner
SWI-Prolog execution for LLMs with CLP(FD) and recursion — boosts logic/constraint accuracy from 73% to 90% on a 30-problem benchmark.
Text Classification (Model2Vec)
A server for text classification using static embeddings from Model2Vec, supporting multiple transports like stdio and HTTP/SSE.
MCP Server
Automate data science stages using your own CSV data files.
Creatify
MCP Server that exposes Creatify AI API capabilities for AI video generation, including avatar videos, URL-to-video conversion, text-to-speech, and AI-powered editing tools.
OpenZeppelin MCP Servers
Model Context Protocol Servers Repository for OpenZeppelin Products
ucn
Universal Code Navigator - a lightweight MCP server that gives AI agents call-graph-level understanding of code. Instead of reading entire files, agents ask structural questions like: "who calls this function", "what breaks if I change it", "what's unused", and get precise, AST-verified answers. UCN parses JS/TS, Python, Go, Rust, Java, and HTML inline scripts with tree-sitter, then exposes 28 navigation commands as a CLI tool, MCP server, or agent skill.
