Weather-MCP
by Efrat-Fr
README.md
# š¤ļø ā ×Ŗ××××Ŗ ××× ×××××Ø ××ש×Ø××
פ×Ø×××§× ××××× ×פ××Ŗ×× **MCP (Model Context Protocol)**: ×”××× (Agent) ××××”×” LLM ש××××¢ ×ש×××£ ×Ŗ××××Ŗ ××× ×××××Ø ××¢×Ø×× ××ש×Ø×× ××××Ø×"×, ×××¢× ××Ŗ ×¢××× ××©×¤× ××פש××Ŗ ×צ'×× ×©×××Ø××× ×.
---
## šÆ ×××Ø×Ŗ ×פ×Ø××ק×
××× ××Ŗ ש×Ø×Ŗ MCP ×××¢××× ×©"××××" ××Ŗ ×-LLM ××צע ×ש××× ×©××× ×× ××××¢ ××× ā ×ש×××£ ×Ŗ××××Ŗ ××× ×××××Ø ×××Ŗ×Ø ×ש×Ø××× ×©××× ×× API.
××”××× ×¢××©× ×××Ŗ ×ש×Ŗ× ××Ø×××:
1. **ש×Ø×Ŗ ×ש×Ø×× (`weather-Israel`)** ā ××××× ×פ××¤× ××××Ŗ× ×¢× **Playwright**: פ××Ŗ× ××Ŗ [weather2day.co.il/forecast](https://www.weather2day.co.il/forecast), ××פש ×¢××Ø, ××××Ø ×××Ŗ×, ××× **×××ׄ ××Ŗ ×Ŗ××× ××£ ××Ŗ××××Ŗ** ××××× ×××Ŗ× ×-LLM ××× ×©××¢× × ×עצ×× (××ש×Ŗ **RAG**).
2. **ש×Ø×Ŗ ××Ø×"× (`weather-USA`)** ā ש×××£ ×Ŗ××××Ŗ ×××Ŗ×Ø×¢××Ŗ ××Ø× ×-API ××Øש×× ×©× ×-NWS (National Weather Service).
×-**Host** ××××Ø ××Ŗ ×× ×ש×Ø×Ŗ×× ×-LLM (Gemini, ××Ø× ×-API ××Ŗ×××-OpenAI), ×××”×£ ××× ××××××××Ŗ ××Ŗ ×× ×-Tools, ×××Ø×ׄ ×××××Ŗ צ'×× ×©×× ×-LLM ××××Ø ××××× ××× ××ש×Ŗ×ש ××פע×× ×××Ŗ× ××× ×××Ø ×× ×¢× ×©××Ŗק×××Ŗ ×Ŗש×××.
---
## šļø ××× × ×פ×Ø××ק×
```
project-template/
āāā host.py # צ'×× ×××Ø××× × ×©××××Ø ××Ŗ ×-LLM ××× ×©×Ø×Ŗ× ×-MCP
āāā client.py # MCP Client ×× ×Ø× (××Ŗ×××Ø ×ש×Ø×Ŗ, ××Ø×ׄ Tools)
āāā weather_USA.py # ש×Ø×Ŗ MCP ×××Ø×"× ā ××Ø× NWS API
āāā weather_Israel.py # ש×Ø×Ŗ MCP ××ש×Ø×× ā ××Ø× ××××× ×פ××¤× (Playwright)
āāā pyproject.toml # ×Ŗ×××××Ŗ ×פ×Ø××ק×
āāā README.md
```
### ×-Tools ×©× ×©×Ø×Ŗ ×ש×Ø××
| # | Tool | ×Ŗפק×× |
|---|------|-------|
| 1 | `open_weather_forecast_israel` | פ××Ŗ× ×פ××¤× Chromium ××× ××× ×××Ŗ×Ø ××Ŗ××××Ŗ |
| 2 | `enter_weather_forecast_city_israel` | ×ק××× ×©× ×¢××Ø ×ש×× ×××פ×ש |
| 3 | `select_weather_forecast_city_israel` | ××××Ø ××Ŗ ××¢××Ø ××Ø×ש×× × ××Øש×××Ŗ ××צע××Ŗ |
| 4 | `get_weather_forecast_content_israel` | ×××ׄ ××Ŗ ×Ŗ××× ××£ ××Ŗ××××Ŗ (×××× iframes) ××××××Ø ×××Ŗ× ×-LLM |
> š” ש××ש×Ŗ ××Ø×ש×× ×× ×××ק×× ×××Ŗ× ×פ××¤× ××Ø× ××¦× ×××××× (`_page`), ×× ×××× ×Øצ×× ××××Ŗ× ×Ŗ××××-ש×Ø×Ŗ. ××Ø×××¢× ×¢×××Ø ×¢× **×× ×-frames** ×××£, ×× ××Ŗ××××Ŗ עצ×× × ××¢× ×Ŗ ××Ŗ×× `<iframe>` ש×-`body` ××Ø××©× ×× ×Ø×××.
---
## āļø ××Ŗ×§× × ×××Øצ×
### ××Ø×ש××Ŗ ×ק×××××Ŗ
- Python ā„ 3.13
- [uv](https://docs.astral.sh/uv/) (×× ×× ××”×××× ×××Ŗ×××××Ŗ)
- ×פ×Ŗ× API ×-Gemini ([ק×××Ŗ ×פ×Ŗ× ××× ××](https://aistudio.google.com/apikey))
### ש××××
```bash
# 1. ××Ŗ×§× ×Ŗ ××Ŗ×××××Ŗ ××ק××Ŗ ×”××××Ŗ ××¢××××
uv sync
# 2. ××Ŗ×§× ×Ŗ ×פ××¤× Chromium ×¢×××Ø Playwright
uv run playwright install chromium
```
### ××××Ø×Ŗ ×ש×Ŗ× × ×”××××
צ×Ø× ×§××ׄ `.env` ××Ŗ×ק×××Ŗ ×פ×Ø××ק×:
```env
GEMINI_API_KEY=your_api_key_here
GEMINI_MODEL=gemini-2.0-flash
```
### ××Øצ×
```bash
uv run host.py
```
××××Ø ××פע×× ×Ŗ×פ××¢ ש××Ø×Ŗ `Query:` ā ×ק×××× ×©××× (×× `quit` ××צ×××).
---
## š¬ ×××××××Ŗ ×ש××××Ŗ ש××”××× ××××¢ ××¢× ××Ŗ ×¢××××
### ×Ŗ××××Ŗ ××ש×Ø×× (Playwright)
> × ×¤×Ŗ× ×××× ×פ××¤× ×©×× ×Ø×××× ××Ŗ ××£ ××Ŗ××××Ŗ, ××-LLM ×× ×¢×× × ×צ'××.
- "×× ××Ŗ××××Ŗ ××Ŗ× ××××?"
- "××× ××¢×××Ŗ צפ××××Ŗ ×××Ø ×××Ø×ש×××?"
- "××× ××× ××××××Ø ××××¤× ××××?"
- "×Ŗפ×Ŗ×× ×× ××Ŗ ××Ŗ××××Ŗ ××××Ø ×©××¢"
### ×Ŗ××××Ŗ ×××Ŗ×Ø×¢××Ŗ ×××Ø×"× (NWS API)
- "What's the weather forecast for San Francisco?" *(latitude/longitude)*
- "Are there any weather alerts in California?"
- "Show me active weather alerts for NY"
---
## š§© ××× ×× ×¢××× (×Ŗ×Øש×× ××Ø×××)
```
×ש×Ŗ×ש ā "×× ××Ŗ××××Ŗ ××Ŗ× ××××?"
ā
ā¼
Host āāāŗ LLM (Gemini) ××××Ø Tools ××פע××
ā
ā¼ (ש×Ø×Ŗ ×ש×Ø××, ××× ×××Ø ××)
open ā enter("×Ŗ× ××××") ā select ā get_content
ā
ā¼
×Ŗ××× ××Ŗ××××Ŗ ××××Ø ×-LLM (RAG)
ā
ā¼
LLM ×××Ŗ× ×Ŗש××× ××©×¤× ××פש××Ŗ ×צ'×× āØ
```
---
## š ××¢×Ø××Ŗ
- ×-LLM ××× ×× ×©××××× ×××× Tools ××פע×× ×××××× ×”××Ø ā ×× ××Ŗ×× × ×××××§× ×§×©×××.
- ×©× × ×§××¦× ×©×Ø×Ŗ = ×©× × ×Ŗ×××××× × ×¤×Ø×××, ×××× ×× ××¦× ×ש××Ŗ×£ (××× ××פ××¤× ×פ×Ŗ××) ×× ××Ŗ×× ×©×Ø×Ŗ ××× ××××.
TDQS
A3.8/5.0
Scored across 4 tools
Disambiguation4/5
Each tool covers a distinct workflow step: opening the page, typing a city, selecting an autocomplete result, and extracting content. The main ambiguity is between open_weather_forecast_israel and get_weather_forecast_content_israel, since both could sound like they return forecast data without reading the descriptions carefully.
Naming Consistency5/5
All tool names follow the same verb-first snake_case pattern and consistently include weather_forecast and israel context. This makes the order and purpose of the tools predictable.
Tool Count5/5
Four tools is appropriate for the narrow browser-automation workflow this server provides. Each tool contributes one essential step, and the set is neither bloated nor too thin.
Completeness4/5
The tool surface covers the full workflow from opening the forecast site to retrieving the forecast text for a chosen city. It lacks fallback or reset tools, but those are not essential for the core task.
Maintenance
ActivitySlowing
ResponsivenessNo issues