Weather-MCP-with-Playwright
An MCP server that uses Google Gemini and Playwright to fetch current weather for Israeli cities, extracting data from live websites to answer queries in Hebrew or English.
README
AI Weather Agent with MCP, Gemini and Playwright
Overview
This project implements an AI Agent that retrieves current weather information for cities in Israel using the Model Context Protocol (MCP), Google Gemini, and Playwright.
When the user asks for the weather in a city, the agent opens a weather website, searches for the requested city, extracts the weather information from the page, and returns an answer based on the website's content.
The project also includes a simple retrieval step, where the weather information is extracted from the web page and provided to the language model as additional context before generating the final response.
Technologies
- Python
- Google Gemini API
- MCP (Model Context Protocol)
- Playwright
- AsyncIO
- python-dotenv
Project Structure
host.py # Main chat application
client.py # MCP client
weather_Israel.py # MCP weather server
README.md
requirements.txt
How It Works
- The user asks for the weather in an Israeli city.
- Gemini selects the appropriate MCP tools.
- Playwright opens the weather website.
- The requested city is entered into the search box.
- The city is selected from the autocomplete list.
- The weather page is loaded.
- The weather information is extracted from the page.
- The extracted text is returned to Gemini.
- Gemini generates the final answer using the extracted information.
Features
- Supports weather queries for cities in Israel.
- Accepts city names in Hebrew or English.
- Uses Playwright to navigate a live weather website.
- Extracts weather information directly from the website.
- Provides the extracted content to the language model before answering.
- Uses the website content instead of relying on the model's internal knowledge.
Installation
Clone the repository:
git clone https://github.com/YisNiz/AI-MCP-with-RAG-project
Install the required packages:
pip install -r requirements.txt
Create a .env file containing:
GEMINI_API_KEY=YOUR_API_KEY
Install Playwright browsers:
playwright install
Run the project:
python host.py
Example Questions
- What is the weather in Jerusalem?
- Weather in Tel Aviv
- מזג האוויר בחיפה
- מה מזג האוויר בבאר שבע?
Notes
- The weather information is retrieved from a live weather website.
- The language model is instructed to answer using the extracted website content.
- The project demonstrates the integration of an LLM with MCP tools and browser automation.
Author
Yisca Nazri
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。