Usgs Mrdata MCP server

@pipeworx/usgs-mrdata

The USGS Mineral Resources Data System (MRDS) — ~300,000 mines, prospects, occurrences and processing plants worldwide, with commodity, deposit type, development status, production history and bibliography.

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

Tools

• mrdatasearchdeposits(bbox?, name_contains?, commodity?, limit?) — sites with deposit id, name, development status, coordinates and commodity codes.
• mrdatadeposit(depid, sections?) — the full record for one deposit.
• mrdatacommodities(bbox?, samplesize?) — commodity site counts for an area, or the code reference list.

Auth

Keyless.

Data sources

• https://mrdata.usgs.gov/services/wfs/mrds — OGC WFS point layer (search).
• https://mrdata.usgs.gov/mrds/json/ — full record for one deposit.

Things the next person would otherwise rediscover:

both rejected by name; only GML 2.1.2 and GML 3.1.1 are advertised.

• The WFS speaks GML only. outputformat=geojson and application/json are

and a 1.0.0-style bbox then returns ZERO features with no error at all.

• Use version=1.0.0 for bbox queries. WFS 1.1.0 flips EPSG:4326 to lat,lon

wildcard works, and is what exact lookup uses.

• PropertyIsEqualTo on depid fails server-side.** PropertyIsLike with no

form answers HTTP 400 with an empty body.

• The per-deposit JSON is a PATH, /mrds/json/. The query-parameter

letters (SDG sand and gravel, STN stone, CLY clay, LST limestone) and qualifies them with a suffix (STNC crushed stone, PGEPT platinum). SDG is the single commonest code in the western US — a two-letter-symbol table leaves it, and most of the database, unnamed.

• Commodity codes are not element symbols. MRDS codes non-metals with three

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/usgs-mrdata/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/mrdata_search_deposits \
  -H 'Content-Type: application/json' \
  -d '{"bbox":"-112.2,33.4,-112.0,33.6","limit":5}'

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

Standalone (no gateway account)

Shortened. The full README is on GitHub.