Israel Weather MCP Server
Enables LLMs to fetch real-time, localized weather forecasts for Israeli cities by using Playwright to autonomously navigate and scrape weather2day.co.il, including handling Hebrew queries and stateful web interactions.
README
🌤️ Israel Weather MCP Server
A custom Model Context Protocol (MCP) server that empowers LLMs to fetch real-time, highly accurate localized weather forecasts for Israeli cities.
Instead of relying on generic global APIs, this agent utilizes Playwright to autonomously navigate to the local Israeli weather portal (weather2day.co.il), interact with the DOM, and extract live data (RAG) directly into the chat context.
🎯 Project Purpose
This project explores the integration of autonomous browser control within an AI Agent architecture. The main learning objectives achieved are:
- Custom MCP Server Development: Building a dedicated server to expose specific tools to an LLM.
- Browser Automation via AI: Using Microsoft's
Playwrightto give the LLM "hands" and "eyes" on the web—allowing it to navigate, search, select from autocomplete dropdowns, and scrape data dynamically. - Overcoming Language & State Barriers: Handling stateful web interactions (waiting for animations, typing sequentially) and ensuring the LLM correctly translates queries to Hebrew before interacting with local UI elements.
🛠️ Technology Stack
- MCP SDK: The official Anthropic library for defining the protocol and exposing tools.
- Playwright: Modern browser automation tool used to programmatically control Chromium.
- uv: Ultra-fast Python package and environment manager.
🚀 How to Run
1. Prerequisites
Ensure you have uv installed on your system.
- Windows (PowerShell):
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" - Mac/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
2. Setup the Environment
Clone the repository, navigate to the project-template folder, and sync the dependencies:
uv sync
3. Install the Browser Engine
Install the Chromium browser required by Playwright:
uv run playwright install chromium
4. Start the Host
Run the interactive terminal chat to start communicating with the Agent:
uv run host.py
💬 Example Queries
Once the Host is running, you can ask the Agent questions like:
- "What is the forecast in Jerusalem?"
- "מה מזג האוויר בתל אביב היום?"
- "Is it going to rain in Haifa tomorrow?"
Watch the magic happen: The Agent will automatically open Chromium, translate the city name to Hebrew, search for it, select the correct autocomplete option, scrape the latest forecast, and provide you with a clean, localized answer right in the terminal!
Developed by SARA DEI
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
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。