MCP server exposing 2 tools for worldbank-climate.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/worldbank-climate/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}get_climate_data — World Bank CCKP climate data for any country: historical observations and CMIP6 climate-model projections. Returns mean temperature, max/min temperature, or precipitation, by emissions scenario. Pass the components as separate args — this tool assembles the brittle composite "indicator code" for you. Values are returned keyed by ISO3 country code; the inner key is "<startYear>-07" (annual/period) or per-season months.
WORKED EXAMPLES (all verified live):
1. Historical annual mean temperature for the USA (defaults): {"geography":"USA"} => tas climatology over 1995-2014, ~10.2°C.
2. Projected warming (anomaly) for the USA mid-century under a high scenario: {"geography":"USA","scenario":"ssp585","period":"2040-2059","product":"anomaly"} => ~2.4°C above baseline.
3. Historical annual precipitation for all countries: {"geography":"all_countries","variable":"pr","product":"climatology","period":"1995-2014","scenario":"historical"} => mm/year per country.
If assembly ever fails for an exotic combination, pass the full composite string via indicator_code instead.list_options — Documents the CCKP indicator-code components and the value combinations that were VERIFIED live against the API. Call this to learn valid variables, scenarios, periods, products, and aggregations before building a get_climate_data request. Takes no arguments.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/worldbank-climate/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io