Water Quality Portal MCP server

@pipeworx/water-quality-portal

US ambient water-chemistry monitoring — station metadata and individual sample results from the joint USGS / EPA / NWQMC Water Quality Portal (NWIS, STORET and STEWARDS in one query surface).

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

• wqpsearchsites(statecode?, countycode?, huc?, bbox?, siteType?, characteristicName?, organization?, limit?) — monitoring stations with coordinates, site type and how many results each holds. At least one filter is required.
• wqpgetresults(siteid?, characteristicName?, statecode?, countycode?, startDate?, endDate?, sampleMedia?, limit?) — individual sample values with unit, method, depth and date.
• wqpresultsnearpoint(latitude, longitude, withinmiles?, characteristicName?, startDate?, endDate?, limit?) — the same results inside a radius.
• wqplistcharacteristics(domain?, text?, limit?) — the controlled-vocabulary spellings the portal demands ("Nitrate", not "nitrate").

Auth

Keyless.

Data sources

• https://www.waterqualitydata.us/data/Station/search — station metadata (GeoJSON).
• https://www.waterqualitydata.us/data/Result/search — sample results (CSV only).
• https://www.waterqualitydata.us/Codes/ — controlled vocabularies (JSON).

Things the next person would otherwise rediscover:

and is rejected for Result; the CSV is parsed in-pack.

• Result/search has no JSON profile. mimeType=geojson works for Station

tools take YYYY-MM-DD and convert, so callers never see it.

• Dates on the wire are MM-DD-YYYY (startDateLo=01-01-2020), not ISO. The

its rows and reports truncated.

• zip=no is mandatory or the response is a zip archive.
• Responses are large — one statewide station query is ~750 KB. Every tool caps

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/water-quality-portal/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, 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 1679+ 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/wqp_search_sites \
  -H 'Content-Type: application/json' \
  -d '{"statecode":"US:06","countycode":"US:06:081","characteristicName":"Nitrate","limit":5}'

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

Standalone (no gateway account)

Shortened. The full README is on GitHub.