@pipeworx/water-levels

Lake and reservoir water levels from satellite radar altimetry — 518 inland water bodies worldwide, 1992 to the present, keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1857+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

Related MCP server: gagelink

What the number means

These are RELATIVE height variations, measured against each lake's own reference datum from a single satellite fly-over. They are not absolute elevation and not height above sea level.

A Caspian Sea reading of -1.88 means 1.88 m below that lake's reference, not below sea level — reporting it as absolute would be wrong by about 28 m for the Caspian alone. Every response carries measurement_note saying so, and the per-lake datum where the source states it.

What the readings are good for: direction and magnitude of change. Whether a lake is rising or shrinking, and by how much, is exactly what altimetry answers well.

The host moved

This dataset is universally cited as USDA FAS G-REALM (ipad.fas.usda.gov). That host now returns 503 on its reservoir pages and 404 on the old per-lake paths. It has moved to NASA GSFC Global Water Monitor, and the redirect only appears inside the old page's markup. The filename convention survived intact — lake000270.10d.2.txt.

Auth

None.

Coverage

Only large water bodies are measurable by radar altimetry; small lakes are not covered at all. The registry ships with the pack (regenerate with scripts/ingest-water-levels.ts); the per-lake series are fetched live, so readings are as current as the source.

Data sources

• NASA GSFC Global Water Monitor — https://earth.gsfc.nasa.gov/gwm/lake/Index

• Per-lake series — https://earth.gsfc.nasa.gov/gwm/timeseries/lake<ID>.10d.2.txt

• Missions: TOPEX/Poseidon, Jason-1/2/3, Sentinel-6A

• Algorithm basis document linked from the index page

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/water-levels/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 1857+ 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/lake_water_level \
  -H 'Content-Type: application/json' \
  -d '{"lake":"Caspian Sea"}'

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

Run it from npm

@pipeworx/mcp-water-levels is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/water-levels/mcp endpoint shown above. It needs network access; there is no offline mode.

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

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

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 Water Levels data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT