mcp-weather-israel-playwright
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | Yes | Anthropic API key for running with the Anthropic SDK (Claude) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| open_weather_forecast_israelA | Open the forecast site and keep the browser/page open for subsequent tools. |
| enter_weather_search_israelA | Enter the city name into the search field and wait for autocomplete results. This uses the shared Page in |
| select_weather_forecast_city_israelA | Select the first autocomplete result (or press Enter) and wait for forecast page to load. |
| extract_weather_data_israelA | Extract and clean the visible forecast text from the current page. This expects that a forecast page is already loaded in the shared Page (i.e., after select_weather_forecast_city_israel). It will attempt to extract the main forecast container text and remove obvious noise like advertisements, links, and short UI strings. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct step in a clear workflow: open site, search, select city, extract data. No overlapping responsibilities.
All tools follow a consistent verb_weather_forecast_city_israel snake_case pattern, making the purpose of each clear.
With 4 tools, the set is well-scoped for the specific task of fetching a weather forecast for an Israeli city. No unnecessary tools or omissions.
The tools cover the primary workflow, but lack error recovery or reset capabilities (e.g., no tool to handle failed city lookup or restart from scratch). Still sufficient for the intended use case.