Weather MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| get_forecastB | Get the weather forecast for a place, anywhere in the world. Args: location: City or place name, e.g. "Delhi", "New Delhi, India", "Tokyo" |
| get_air_qualityB | Get current air quality (AQI and pollutants) for a place, anywhere in the world. Args: location: City or place name, e.g. "Delhi", "Beijing", "Los Angeles" |
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 2 tools
get_forecast and get_air_quality target clearly distinct data domains (weather forecast vs air quality/pollutants), so an agent can unambiguously select between them. Both share a consistent location argument, removing any selection confusion.
Both tools follow the identical verb_noun pattern (get_forecast, get_air_quality) with snake_case throughout. There is no deviation or mixed convention.
Two tools is thin for a weather server's apparent scope; a single data-lookup pattern covers only forecast and air quality. It is functional but borderline sparse for the domain.
Core lookups are covered, but obvious operations are missing: current conditions, historical weather, hourly/daily breakdowns, and severe weather alerts. Agents would hit dead ends for common weather queries.