mcpField
G
Gistemp

Gistemp

Remote
pipeworx.ioScience & Education0Updated 1d ago

About Gistemp

Gistemp is an MCP server for NASA GISTEMP surface-temperature anomaly data. It is intended for climate-data analysis, providing historical time series, the latest global reading and rank, and annual latitude-band anomalies.

Key features

  1. 01Get monthly, annual, and seasonal anomalies
  2. 02Retrieve the latest global anomaly and rank
  3. 03Compare annual anomalies across latitude bands
  4. 04Choose a region and time frequency

Use cases

  1. 01Review long-term temperature trends
  2. 02Check the latest monthly global reading
  3. 03Compare warming across latitude bands

MCP support

Exposes NASA GISTEMP anomaly data through tools for MCP clients, including historical series, the latest global reading, and zonal values. It can run locally over stdio or through the Pipeworx gateway.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/gistemp/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-gistemp

GISTEMP MCP — NASA Goddard Institute for Space Studies Surface Temperature Analysis (free, no auth)

Part of Pipeworx — an MCP gateway connecting AI agents to 1879+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
get_temperature_anomalyNASA 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.
get_latest_anomalyMost 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."
get_zonal_anomaliesNASA 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.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "gistemp": {
      "url": "https://gateway.pipeworx.io/gistemp/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/gistemp/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1879+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/get_temperature_anomaly \
  -H 'Content-Type: application/json' \
  -d '{"region":"global_land_ocean","frequency":"annual"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/get_temperature_anomaly. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "gistemp": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-gistemp"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-gistemp

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Gistemp data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.