Skip to main content
Glama
m0533199321

mcp-playwright-weather-israel

by m0533199321
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WEATHER_HEADLESSNoIf set to 'true', runs browser in headless mode.false
WEATHER_SLOW_MO_MSNoSlow motion delay in milliseconds.0
WEATHER_TIMEOUT_MSNoTimeout for navigation and selectors.45000

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
open_weather_forecast_israelA

Open a browser and navigate to the Israeli weather forecast site.

Call this first. It leaves the browser sitting on the forecast page with the city search box ready. Returns the page title and URL.

enter_weather_forecast_city_israelA

Type an Israeli city name into the forecast search box.

Returns the autocomplete suggestions, numbered from 0. The list is what the
site offers - it may contain neighbourhoods and landmarks as well as the city
itself (typing "חיפה" offers "חוף הסטודנטים, חיפה" before plain "חיפה").
Read the list before choosing, then call select_weather_forecast_city_israel.

Args:
    city: City name, in Hebrew (e.g. "תל אביב", "חיפה", "באר שבע").
select_weather_forecast_city_israelA

Click a city from the autocomplete list and load its forecast page.

Args:
    index: Which suggestion to click, numbered from 0. Defaults to 0, the
        first item - but the first item is not always the city itself, so
        prefer the index whose text matches the city the user asked for.
extract_weather_forecast_israelA

Read the forecast off the page that is currently open, as clean markdown.

Call this after select_weather_forecast_city_israel, and call it with NO
arguments. The defaults already return the current conditions (temperature,
wind, gust, wind direction, humidity, sunrise, sunset, last update) plus three
days of hourly forecast, which is enough for almost any question. Shrinking
the window costs you the data you are about to be asked about.

Args:
    max_days: Days of hourly forecast. Leave unset unless the user explicitly
        asks about several days ahead. Clamped to 1-10.
    max_hours_per_day: Hours per day. Leave unset. Clamped to 3-24.
close_weather_browser_israelA

Close the browser opened by these tools. Safe to call at any time.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.6/5.0

Scored across 5 tools

Disambiguation5/5

Each tool serves a distinct step in the workflow: open, enter city, select suggestion, extract forecast, and close browser. No two tools overlap in purpose, and the descriptions make the sequence clear.

Naming Consistency5/5

All tool names follow a consistent pattern: verb + weather-related noun + location suffix 'israel'. The verbs (open, enter, select, extract, close) are distinct and the naming style is uniformly snake_case.

Tool Count5/5

Five tools is exactly the right size for a focused browser-automation workflow. Each tool is necessary and corresponds to a logical user action, with no redundancy or bloat.

Completeness5/5

The set covers the entire lifecycle from opening the weather site, searching and selecting a city, extracting the forecast, and closing the browser. The extraction tool even offers configurable depth, addressing potential user needs without missing steps.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources