Weather MCP Server
# Weather MCP Server
This project is a Model Context Protocol (MCP) server that provides weather information.
## Features
- Get current weather forecast for a specific latitude and longitude.
- Get active weather alerts for a US state.
## Setup
1. **Install dependencies:**
```bash
pnpm install
```
2. **Build the server:**
```bash
pnpm run build
```
## Running the Server
This server is designed to be run by an MCP client, such as Claude for Desktop.
To configure Claude for Desktop (or a similar MCP client) to use this server, you'll need to point it to the built server. The typical configuration would involve specifying:
- **Command**: `node`
- **Arguments**: `["/ABSOLUTE/PATH/TO/YOUR/PROJECT/mcptest/build/index.js"]`
Replace `/ABSOLUTE/PATH/TO/YOUR/PROJECT/` with the actual absolute path to the `mcptest` directory on your system.
For example, if your project is in `/Users/bohe/Desktop/mcptest`, the argument would be `["/Users/bohe/Desktop/mcptest/build/index.js"]`.
Refer to your MCP client's documentation for specific instructions on how to add and configure an MCP server.
## Development
- Source code is in the `src` directory.
- The main server logic is in `src/index.ts`.
- Build output is in the `build` directory.
## MCP Configuration
The `.vscode/mcp.json` file is provided for VS Code to recognize and potentially debug this MCP server.
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves weather alerts for a state, while the other provides forecasts for a location. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on the need for alerts versus general weather predictions.
Both tools follow a consistent verb_noun naming pattern with hyphens (get-alerts and get-forecast). This uniformity makes the tool set predictable and easy to understand, adhering to a clear convention throughout.
With only 2 tools, the server feels thin for a weather domain, lacking essential operations like current conditions, historical data, or radar imagery. While the tools are well-defined, the count is too low to adequately cover typical weather-related use cases, suggesting an incomplete surface.
The tool set is severely incomplete for a weather server, missing core functionalities such as current weather conditions, historical data, or severe weather details. Agents will face significant gaps when trying to perform common weather-related tasks, leading to potential failures in broader workflows.