modelcontextprotocol/quickstart-resources Official Python Weather MCP server using stdio and the US National Weather Service API.
The server exposes:
1. Clone and prepare the server The official example is intentionally small. Keep it local unless you add authentication, request limits, timeouts, and log redaction before exposing it over a network.
2. Preview Discovery Confirm that the preview lists both tools and does not include local environment secret values. Preview reads definitions; it does not call either weather tool.
3. Upload the inventory Open MCPs → weather-mcp and confirm the two schemas.
Screenshot placeholder /images/examples/weather-mcp-inventory.png showing the provider, last Discovery status, and both tools.
4. Create Gateway rules A useful first configuration is:
5. Test the governed server In MCP Inspector:
call get_alerts with state: NY and confirm it runs under Observe;
call get_forecast with latitude: 38.8977 and longitude: -77.0365;
open Operator Tasks in GroundForge;
approve or reject the forecast request.
The reviewed call must not run before approval.
6. Review the records Check the Gateway decision, whether the tool executed, the reviewed input, and any later Drift after changing a tool schema.
Continue with Discovery , Observations , and Drifts , Gateway Rules , or CLI MCP Workflows . Last modified on July 27, 2026
