About MAAT MCP Restaurant Finder
MAAT MCP Restaurant Finder is a remote MCP server for location-based restaurant search and recommendations. It supports nearby searches, random picks, and category-based discovery such as Korean, Chinese, Japanese, and Western food.
Key features
- 01Search for nearby restaurants
- 02Get a random nearby recommendation
- 03Search by cuisine category
- 04Expose restaurant search results as a resource
Use cases
- 01Find restaurants around a location
- 02Choose a random nearby place to eat
- 03Narrow restaurant searches by cuisine
MCP support
The remote MCP server provides restaurant search and recommendation tools, a restaurant-results resource, and a restaurant-search prompt to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMAAT MCP Restaurant Finder
맛집 검색 및 추천 서비스를 제공하는 remote MCP(Model Context Protocol) server입니다.
주요 기능
- 맛집 검색: 사용자의 위치 기반으로 주변 맛집을 검색합니다.
- 랜덤 추천: 현재 위치 기반으로 랜덤 맛집을 추천합니다.
- 카테고리별 검색: 한식, 중식, 일식, 양식 등 카테고리별 맛집 검색을 지원합니다.
기술 스택
- Python 3.8+
- FastMCP 0.4.1+
- Google Maps API
설치 방법
- 저장소 클론
git clone https://github.com/akateddy/maat_mcp_server.git
cd maat_mcp_server
- 의존성 설치
pip install -r requirements.txt
- 환경 변수 설정
.env파일을 생성하고 다음 변수들을 설정합니다:
GOOGLE_MAPS_API_KEY=your_google_maps_api_key
IPLOCATION_API_KEY=your_iplocation_api_key
실행 방법
python main.py
API 엔드포인트
리소스
maat://restaurant_results: 맛집 검색 결과 리소스
프롬프트
맛집 검색: 맛집 검색 프롬프트
도구
find_restaurants: 맛집 검색 도구recommend_random_restaurant: 랜덤 맛집 추천 도구
프로젝트 구조
maat_mcp_server/
├── main.py # 메인 애플리케이션
├── requirements.txt # 의존성 목록
└── maat_mcp/ # 핵심 패키지
├── api/ # API 클라이언트
├── handlers/ # 비즈니스 로직
└── util/ # 유틸리티 함수
라이선스
MIT License
claude_desktop_config 설정 방법
"restaurants_finder": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8000/sse"
],
"env": {
"GOOGLE_MAPS_API_KEY": "{YOUR_GOOGLE_MAPS_API_KEY}"
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.