MCP server exposing 3 tools for nasa-gibs.
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/nasa-gibs/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}gibs_list_layers — "What NASA satellite imagery layers are there for wildfires / sea ice / aerosols?" — search NASA GIBS, the ~1,300-layer imagery catalogue behind NASA Worldview. AUTHORITATIVE for which global satellite imagery products exist and what time span each covers: true-colour MODIS/VIIRS mosaics, thermal anomalies, sea-surface temperature, aerosol optical depth, snow and ice cover, vegetation index, night lights. Returns each layer's identifier (the id the other two tools take), human title, resolution grid, image format and the date range it is available for.gibs_layer_info — Everything NASA GIBS publishes about one imagery layer: its full title, the dates it actually covers (as ISO 8601 start/end/period ranges), the most recent date available, native tile grid and zoom depth, image format, geographic extent, colour map and legend URLs, and the raw WMTS tile template. Call this before gibs_tile_url when you need to know which dates exist for a layer.gibs_tile_url — "Give me the satellite image of Los Angeles on 2026-09-10" — build a ready-to-fetch NASA GIBS image tile URL for a layer, a date and a place. Give a latitude/longitude and a zoom level and it computes the WMTS tile row/column for you; give tile_row/tile_col directly if you already have them. Returns the tile URL plus the tile's own geographic bounds and the resolved date, so the caller can show or download the actual imagery.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/nasa-gibs/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io