Weather MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | Yes | Groq API key required for the interactive chat client (LLM). This is mentioned in the project setup, although it may primarily be used by the client rather than the MCP server itself. |
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_alertsA | MCP Tool: Get active weather alerts for a US state. This tool is exposed to MCP clients and can be invoked by AI agents. It fetches from the NWS API and returns formatted alert information. Args: state: Two-letter US state code (e.g. CA, NY, TX) Returns: Formatted string of all active alerts, or a message if none found |
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 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently follows a consistent naming pattern. The tool name 'get_alerts' uses a verb_noun structure, which is clear and appropriate for its function.
A single tool is too few for a weather server's apparent scope, which typically includes forecasts, current conditions, and alerts. This feels thin and limits functionality, though it is focused on one specific task.
The tool set is severely incomplete for a weather domain, covering only alerts for US states. Obvious gaps include lack of forecast retrieval, current weather data, international support, or historical data, which will cause agent failures in broader weather-related tasks.