NWS Weather MCP Sample
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 a National Weather Service forecast for a US latitude/longitude. Args: latitude: Latitude in decimal degrees (e.g. 40.7128 for NYC). longitude: Longitude in decimal degrees (e.g. -74.0060 for NYC). |
| get_alertsA | Get active National Weather Service alerts for a US state. Args: state: Two-letter US state code (e.g. CA, NY, TX). |
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
The two tools are clearly distinct - one retrieves forecasts by coordinates while the other retrieves alerts by state. There is no overlap in purpose or inputs, so an agent cannot confuse them.
Both tools follow a consistent get_noun pattern (get_forecast, get_alerts), which is clean and predictable. Minor deviation is that one uses a noun naming forecasts while the other names alerts, but the get_ prefix unifies them.
Two tools feels very thin for the NWS weather domain, which normally includes observations, hourly forecasts, marine forecasts, radar, and point metadata. The count is at the low boundary of what's considered reasonable.
The surface is missing obvious operations like current conditions/observations, hourly forecasts, forecast office information, and marine/hydrological products. An agent needing current weather conditions would dead-end entirely with just forecast and alerts.