Xome

US residential foreclosure/bank-owned (REO)/short-sale auction calendar and property facts from xome.com.

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: Zillow MCP Server

The bid-price gap — resolved (outcome (a))

The dollar amount is not in the page's schema.org markup (Offer.price is absent even on a confirmed-sold listing — verified: a "Sold to Bank" listing's Offer shows only availability: "https://schema.org/SoldOut", no price). It lives instead in the same page's Next.js App Router RSC flight payload (self.__next_f.push([1, "..."]) chunks) as an embedded "auctionInfo":{...} object carrying bidAmount, bidType and liveEventStatus. This pack extracts it (regex + brace-matching on the concatenated, unescaped flight chunks) rather than shipping calendar-only.

Every price is labeled by its actual state — never presented as a bare number a caller could mistake for something it isn't:

Auth

None. Keyless, no login required to browse listings.

Data sources

• xome.com/sitemap/auctions/sitemap-auctionrecords0.xml.gz — bulk discovery of individual listing URLs.

• xome.com/auctions/{state}[/{county}] — paginated listing pages; the ItemList application/ld+json block carries full property facts for every row with no extra request per item.

• xome.com/auctions/{listing-slug} — one listing's RealEstateListing / SingleFamilyResidence+Product / Offer / SaleEvent JSON-LD graph, plus the embedded auctionInfo RSC data for price.

robots.txt

Disallows account/dashboard paths, /api/, /signalr/ and a few report endpoints — none of which this pack touches; everything here comes from the plain public listing HTML already served to any visitor. Per Bruce's 2026-09-01 ruling, public unauthenticated content is buildable regardless of robots; this pack still deliberately stays off every disallowed path since the same data is already present on the page it fetches.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/xome/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/xome_search \
  -H 'Content-Type: application/json' \
  -d '{"state":"ca","county":"fresno"}'

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

Run it from npm

@pipeworx/mcp-xome 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/xome/mcp endpoint shown above. It needs network access; there is no offline mode.

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

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 Xome data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT