Cover image
Try Now
2025-04-14

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

Yargitay MCP Server

A FastMCP server that provides tools to search and retrieve court decisions from the Yargitay Karar Arama website (https://karararama.yargitay.gov.tr/).

Features

  • Search court decisions using keywords and various parameters
  • Retrieve full text of court decisions by ID
  • Quick search functionality for simple keyword-based searches

Installation

Using uv (recommended)

  1. Clone this repository
  2. Install dependencies using uv:
    uv sync
    

Alternatively, you can create a virtual environment:

uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv sync

Using pip

  1. Clone this repository
  2. Install dependencies:
    pip install -r requirements.txt
    

Project Structure

yargitay-mcp/
├── yargitay/           # Main package
│   ├── __init__.py     # Package initialization
│   ├── models.py       # Data models
│   ├── client.py       # API client for Yargitay
│   └── server.py       # FastMCP server implementation
├── tests/              # Test suite
│   └── test_yargitay.py # Tests for the Yargitay server
├── examples/           # Example scripts
│   └── client_example.py # Example client usage
├── server.py           # Main entry point
├── pyproject.toml      # Project configuration
└── requirements.txt    # Dependencies (for pip)

Usage

Running the server with FastMCP

There are several ways to run the server:

Development mode (recommended for testing)

fastmcp dev server.py

This launches the interactive MCP Inspector for testing.

Install for Claude Desktop integration

fastmcp install server.py --name "Yargitay Karar Arama"

Direct execution

python server.py

This will start the server with SSE transport on http://localhost:8888.

Running the tests

To run the test suite with pytest:

pytest

Or with the unittest module:

python -m unittest discover tests

Example Client

You can find a simple example client in the examples/client_example.py file:

python examples/client_example.py

Available Tools

The MCP server provides the following tools:

  1. quick_search(keyword, page, page_size) - Simplified search with just a keyword
  2. search_court_decisions(search_params) - Advanced search with multiple parameters
  3. get_decision_by_id(decision_id) - Retrieve the full text of a court decision

Example Usage

  1. Search for decisions containing the word "test":

    quick_search(keyword="test")
    
  2. Get the full text of a decision by its ID:

    get_decision_by_id(decision_id="1126134100")
    
  3. Advanced search with multiple parameters:

    search_court_decisions(
        search_params={
            "keyword": "test", 
            "department": "10. Hukuk Dairesi", 
            "karar_yil": "2025"
        }
    )
    

Development

Setting up the development environment

# Install development dependencies
uv sync --dev

# Run tests
pytest

Implementation Notes

This server follows the FastMCP pattern of directly exporting a mcp variable, which is the FastMCP instance, as recommended in the FastMCP documentation. This allows for direct access to the MCP instance by the FastMCP CLI and other tools.

相关推荐

  • av
  • Ejecute sin esfuerzo LLM Backends, API, frontends y servicios con un solo comando.

  • 1Panel-dev
  • 🔥 1Panel proporciona una interfaz web intuitiva y un servidor MCP para administrar sitios web, archivos, contenedores, bases de datos y LLM en un servidor de Linux.

  • WangRongsheng
  • 🧑‍🚀 全世界最好的 llM 资料总结(数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Resumen de los mejores recursos del mundo.

  • rulego
  • ⛓️Rulego es un marco de motor de regla de orquestación de componentes de alta generación de alto rendimiento, de alto rendimiento y de alto rendimiento para GO.

  • sigoden
  • Cree fácilmente herramientas y agentes de LLM utilizando funciones Plain Bash/JavaScript/Python.

  • hkr04
  • SDK liviano C ++ MCP (Protocolo de contexto del modelo)

  • RockChinQ
  • 😎简单易用、🧩丰富生态 - 大模型原生即时通信机器人平台 | 适配 Qq / 微信(企业微信、个人微信) / 飞书 / 钉钉 / Discord / Telegram / Slack 等平台 | 支持 Chatgpt 、 Deepseek 、 DiFy 、 Claude 、 Gemini 、 Xai 、 PPIO 、 Ollama 、 LM Studio 、阿里云百炼、火山方舟、 Siliconflow 、 Qwen 、 Moonshot 、 Chatglm 、 SillyTraven 、 MCP 等 LLM 的机器人 / Agente | Plataforma de bots de mensajería instantánea basada en LLM, admite Discord, Telegram, WeChat, Lark, Dingtalk, QQ, Slack

  • dmayboroda
  • Trapo conversacional local con contenedores configurables

  • modelscope
  • Iniciar aplicaciones de múltiples agentes empoderadas con Building LLM de manera más fácil.

  • paulwing
  • Un repositorio de pruebas creado con el servicio MCP

  • evilsocket
  • El kit de desarrollo de agentes simples.

    Reviews

    3 (2)
    Avatar
    user_CgFCTZw3
    2025-04-23

    I've been using yargitay-mcp for a while now, and it has truly streamlined my workflow. The interface is user-friendly and the functionalities are comprehensive, making it an outstanding choice for anyone in need of a reliable MCP application. MAkcanca has done an excellent job with this tool. Highly recommend!

    Avatar
    user_mqrAgmoe
    2025-04-23

    As a devoted user of the yargitay-mcp, I must say this application developed by MAkcanca has exceeded my expectations. Its intuitive interface and robust features in managing cases are unmatched. The seamless navigation and user-friendly design make it an essential tool. Highly recommended for anyone in need of an efficient case management solution!