Run the weather server in a separate terminal
LocalAbout Run the weather server in a separate terminal
A LangGraph agent example that connects to separate math and weather MCP servers. It is for developers exploring this setup; the README gives commands to start the weather server and agent.
Key features
- 01LangGraph agent
- 02Math and weather server setup
- 03Environment-based API keys
Use cases
- 01Trying an agent with math services
- 02Running weather and math servers separately
MCP support
The agent integrates with MCP servers for math and weather. The weather server is started separately, and the math server path is configured in agent.py.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMECreate an env and install the dependencies:
uv venv
source .venv/bin/activate
uv pip install -r pyproject.toml
Don't forget: add your API Keys to .env
Run the weather server in a separate terminal
python mcp/weather_server.py
Adjust the path to the math server in agent.py
Run the agent
python agent.py
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.