Product Management MCP Server
Provides tools for managing a product catalog, including functions to list, add, and retrieve product statistics. It enables AI agents to perform inventory operations and data analysis through a standardized interface.
README
AI Engineer Test Task
Реализация тестового задания:
- MCP сервер на FastMCP (stdio, 4 инструмента)
- LangGraph агент с mock LLM и custom tools
- FastAPI endpoint для общения с агентом
- Dockerfile + docker-compose
- Набор тестов (3+)
Стек
- Python 3.11+
- FastMCP
- MCP Python SDK
- LangGraph + langchain-core
- FastAPI + Uvicorn
- Pytest
Структура проекта
.
├── app
│ ├── agent
│ │ ├── graph.py
│ │ ├── mcp_client.py
│ │ ├── mock_llm.py
│ │ └── tools.py
│ ├── main.py
│ └── schemas.py
├── mcp_server
│ ├── data/products.json
│ └── server.py
├── tests
│ ├── test_agent.py
│ ├── test_api.py
│ └── test_mcp_server.py
├── Dockerfile
├── docker-compose.yml
└── requirements.txt
MCP инструменты
В mcp_server/server.py реализованы tools:
list_products(category: str | None = None)get_product(product_id: int)add_product(name: str, price: float, category: str, in_stock: bool = True)get_statistics()
Особенности:
- transport:
stdio - декораторы
@mcp.tool - type hints + docstrings
ValueError, если товар не найден
Агентный flow (LangGraph)
- Узел
analyze: mock LLM (rule-based) разбирает запрос и формируетaction + params. - Узел
execute: вызывает MCP tools через stdio-клиент + custom tools. - Узел
respond: формирует финальный текст пользователю.
Custom tools:
calculate_discount- форматтеры ответа (
format_products,format_statistics)
API
POST /api/v1/agent/queryGET /health
Пример запроса:
curl -X POST "http://localhost:8000/api/v1/agent/query" \
-H "Content-Type: application/json" \
-d '{"query":"Покажи все продукты в категории Электроника"}'
Запуск
Вариант 1: Docker Compose (рекомендуется)
docker compose up --build
API будет доступен на http://localhost:8000.
Вариант 2: Локально
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
uvicorn app.main:app --reload --port 8000
Тесты
pytest -q
Покрытие требований тестами:
tests/test_mcp_server.py:- добавление продукта
- статистика
- обработка ошибки
ValueError
tests/test_agent.py:- вычисление средней цены
- расчет скидки через custom tool
tests/test_api.py:- проверка
POST /api/v1/agent/query
- проверка
Примеры запросов к агенту
Покажи все продукты в категории ЭлектроникаКакая средняя цена продуктов?Добавь новый продукт: Мышка, цена 1500, категория ЭлектроникаПосчитай скидку 15% на товар с ID 1
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.