mcp-weather
# mcp-weather、mcp-flomo for MCP Server
A Model Context Protocol server
> **2025-02-22** · 今天完成了第一个 MCP 服务器的开发,将写笔记能力接入了 flomo。
> **2025-03-09** · 本地ollama + ChatBox +mcp 实现了查询天气情况,并将结果成功返回ChatBox显示。
This is a TypeScript-based MCP server that implements a simple notes system. It demonstrates core MCP concepts by providing:
- Resources representing text notes with URIs and metadata
- Tools for creating new notes
- Prompts for generating summaries of notes
## Features
### Resources
- List and access notes via `note://` URIs
- Each note has a title, content and metadata
- Plain text mime type for simple content access
### Tools
- `create_note` - Create new text notes
- Takes title and content as required parameters
- Stores note in server state
### Prompts
- `summarize_notes` - Generate a summary of all stored notes
- Includes all note contents as embedded resources
- Returns structured prompt for LLM summarization
## Development
Install dependencies:
```bash
npm install
```
Build the server:
```bash
npm run build
```
For development with auto-rebuild:
```bash
npm run watch
```
## Installation
To use with Claude Desktop, add the server config:
On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"test-mcp": {
"command": "/path/to/test-mcp/build/index.js"
}
}
}
```
### Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:
```bash
npm run inspector
```
The Inspector will provide a URL to access debugging tools in your browser.
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: query_weather deals with weather data retrieval, while write_note handles note creation. There is no overlap or ambiguity between these unrelated functions, making misselection highly unlikely.
The tools use a consistent verb_noun pattern (query_weather, write_note), which is good. However, the server name 'mcp-weather' suggests a weather-focused domain, making write_note an outlier that breaks thematic consistency, though the naming style itself is uniform.
With only 2 tools, the set feels too thin for the implied scope. The server name indicates a weather domain, but write_note is unrelated, leaving weather functionality underdeveloped (e.g., no forecast, alerts, or location-based queries). This minimal count does not adequately cover the expected domain.
The tool surface is severely incomplete. For a weather server, basic operations like getting forecasts, historical data, or location searches are missing, and write_note is irrelevant to the domain. This creates significant gaps that will cause agent failures in weather-related tasks.