Austin Animal Services MCP server

@pipeworx/austin-animal-services

Live shelter intake and outcome records from the Austin Animal Center (Austin, TX) — recent intakes, animal lookup, and outcome summaries (adoptions, transfers, euthanasia, etc).

Part of Pipeworx — an MCP gateway connecting AI agents to 1558+ live data sources.

Tools

intakes (default last 30 days), with a total count for the window plus a page of rows. Answers "how many dogs did Austin Animal Center take in last month".

• austinrecentintakes(days?, animaltype?, intaketype?, limit?) — recent

animal by id, name, or breed across both intake and outcome records.

• austinsearchanimal(animal_id?, name?, breed?, limit?) — look up an

by outcometype, animaltype, or month.

• austinoutcomessummary(since?, group_by?) — counts of outcomes grouped

Auth

Keyless. Pass your own Socrata app token via _apiKey for higher rate limits.

Data sources

Center Intakes (current, hourly refresh, live since May 2025).

• — Austin Animal

Center Outcomes (current, hourly refresh, live since May 2025).

• — Austin Animal

The city migrated to a new shelter system (ShelterBuddy) in May 2025. The older "Austin Animal Center Intakes/Outcomes (10/01/2013 to 05/05/2025)" datasets (wter-evkm / 9t4d-g238) are now frozen historical snapshots with no rows after 2025-05-19 — this pack deliberately uses the current, hourly-refreshed successors instead so "recent" and "last month" queries answer correctly. Socrata paging is $limit/$offset; every call in this pack sets $limit explicitly. Field names differ between the current and historical datasets (e.g. intake timestamp is source_date on the current dataset, datetime on the historical one) — don't assume they're interchangeable.

Quick Start

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

{
  "mcpServers": {
    "austin-animal-services": {
      "url": "https://gateway.pipeworx.io/austin-animal-services/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/austin-animal-services/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 1558+ 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/austin_recent_intakes \
  -H 'Content-Type: application/json' \
  -d '{"days":30,"animal_type":"Dog"}'

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

Standalone (no gateway account)

Shortened. The full README is on GitHub.