Before you begin
You need:- access to platform.groundforge.ai;
- an Organization and Workspace;
- the
gforgeCLI for command-line steps; - Python 3.10 or newer;
- the
groundforge-langchainwheel supplied with your GroundForge release for the Agent example.
Path A: Weather MCP
modelcontextprotocol/quickstart-resources
Official Python MCP server with
get_alerts(state) and get_forecast(latitude, longitude).Path B: LangChain weather Agent
groundforgeai/demo
GroundForge external-Agent examples using automatic Channel input handling and explicit adapters.
- LangChain Agent Example — automatic Channel input handling;
- LangChain Agent with Adapters — explicit input and output conversion.
What to check in GroundForge
After the first request, confirm:- the Agent or MCP provider is visible in the selected Workspace;
- Discovery lists the expected weather capability;
- the Gateway shows the action you selected;
- an Operator Task appears when the action is Review;
- the Trace shows the Channel input, decision, capability call, and response.

