Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for live weather data
This repo provides a Go-based MCP server that connects an agent to WeatherAPI and returns current weather for a city. You can run it locally over stdio in Claude Desktop or remotely over SSE.
Builders who want their MCP-capable agent to retrieve live weather data.
You can ask your agent for current weather without wiring up a custom weather integration yourself.
What it does
Current weather tool
Provides a `current_weather` MCP tool that takes a city name and returns live weather data.
Local and remote transport
Supports Claude Desktop local mode with a command path and remote mode with an SSE URL.
Docker packaging
Includes a Dockerfile and run instructions for serving the MCP server in a container.
Test and mock workflow
Uses Go tests and `make generate-mocks` for mock generation during development.
How to get it
- 1Run
go install go.uber.org/mock/mockgen@latest
README
A lightweight Model Context Protocol (MCP) server that enables AI assistants like Claude to retrieve and interpret real-time weather data.
Installing on Claude Desktop
To use your MCP server with Claude Desktop, add it to your Claude configuration:
1. Local mode
{
"mcpServers": {
"weather-mcp-server": {
"command": "/path/to/weather-mcp-server",
"env": {
"WEATHER_API_KEY": "your-api-key"
}
}
}
}
You can get an API key from your personal account on WeatherAPI.
2. Remote mode
{
"mcpServers": {
"weather-mcp-server": {
"url": "http://host:port/sse"
}
}
}
Build from source
You can use go to build the binary in the cmd/github-mcp-server directory.
go build -o weather-mcp-server ./cmd/weather-mcp-server
Using MCP with Docker Containers
1. Build the Docker Image:
docker build -t weather-mcp-server .
2. Run the Docker Container:
docker run -e WEATHER_API_KEY=your-api-key -d --name weather-mcp-server -p 8000:8000 weather-mcp-server
Replace your-api-key with your actual WeatherAPI API key.
Tools
-
current_weather - Gets the current weather for a city
city: The name of the city (string, required)
Project Structure
The project is organized into several key directories:
├── cmd
│ └── weather-mcp-server
├── internal
│ └── server
│ ├── handlers # MCP handlers
│ ├── services # Business logic layer
│ │ ├── core # Core application logic
│ │ └── mock # Mock services for testing
│ ├── tools # MCP tools
│ └── view # Templates for displaying messages
└── pkg
Testing
If you're adding new features, please make sure to include tests for them.
1. Install the mockgen tool:
go install go.uber.org/mock/mockgen@latest
See the installation guide on go.uber.org/mock.
2. Use the following command to generate mock files:
make generate-mocks
3. To run unit tests:
make run-tests
Contributing
Feel free to open tickets or send pull requests with improvements. Thanks in advance for your help!
Please follow the contribution guidelines.
License
This MCP server is licensed under the MIT License.
Files in the repo
- .github
- assets
- cmd
- internal
- pkg
- .gitignore
- Dockerfile
- go.mod
- go.sum
- LICENSE
- Makefile
- README.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros