{
  "markdown": "# mcp-gistemp\n\nGISTEMP MCP — NASA Goddard Institute for Space Studies Surface Temperature\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_temperature_anomaly` | NASA GISTEMP surface temperature anomaly time series (degrees C from 1951-1980 baseline). Pick a region (global_land_ocean, global_land_only, northern_hemisphere, southern_hemisphere) and get monthly + annual + seasonal values back. Use for climate bets (\"will 2026 be the hottest year on record\"), trend comparisons, or cross-source consistency checks against HadCRUT5/Berkeley Earth. Annual frequency returns one row per year (Jan-Dec mean); monthly returns Jan..Dec per year. |\n| `get_latest_anomaly` | Most recent NASA GISTEMP global land+ocean monthly anomaly, plus how it ranks against history. Returns the latest available month, the anomaly value (degrees C from 1951-1980 baseline), the rank of that value among all same-month observations since 1880, and a 12-month trailing mean. Cheaper than get_temperature_anomaly when you only need \"what is the current reading and is it unusual.\" |\n| `get_zonal_anomalies` | NASA GISTEMP annual zonal anomalies (degrees C from 1951-1980 baseline) for 8 latitude bands: global, Northern Hemisphere, Southern Hemisphere, 24N-90N, 24S-24N (tropics), 90S-24S, 64N-90N (Arctic), 44S-24S, etc. Use for regional climate bets (\"will the Arctic warm faster than the tropics in 2026\") or bets framed around polar amplification. |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"gistemp\": {\n      \"url\": \"https://gateway.pipeworx.io/gistemp/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/gistemp/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Gistemp data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 3582,
  "sha": "1c8495c0f6554a9fbbf8a09771b41057e778a03d655734ed27f641ff5b566ea5",
  "repo_slug": "pipeworx-io/mcp-gistemp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_gistemp_f5a10bed/readme"
}