{
  "markdown": "# @pipeworx/nyc-animals\n\nDog licensing and dog-bite records for New York City — reported bite\nincidents by borough, licensed-dog breed counts, and dog lookup by name.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1558+ live data sources.\n\n## Tools\n\n- `nyc_dog_bites(borough?, since?, limit?)` — reported dog bite incidents.\n  If a `since` filter would return zero rows (the dataset is published in\n  periodic batches and can lag), the tool automatically retries without the\n  date bound and returns a `note` explaining the fallback rather than a\n  silent empty result.\n- `nyc_dog_licences_by_breed(breed?, zipcode?, top?)` — licensed-dog counts\n  by breed, or the most common breeds overall.\n- `nyc_search_animal(name, zipcode?, limit?)` — look up a licensed dog by\n  name.\n\n## Auth\n\nKeyless. Pass your own Socrata app token via `_apiKey` for higher rate\nlimits.\n\n## Data sources\n\n- <https://data.cityofnewyork.us/resource/nu7n-tubp.json> — NYC Dog\n  Licensing Dataset.\n- <https://data.cityofnewyork.us/resource/rsgh-akpg.json> — DOHMH Dog Bite\n  Data.\n\nThese are two distinct datasets, not a single intake/outcome shelter feed —\nNYC does not publish a live shelter intake/outcome dataset the way Austin and\nSonoma County do, so this pack's tools match licensing + bite-report data\nrather than the shelter shape. The bite dataset's live max date was\n2025-12-31 as of 2026-09-04 (next batch not yet posted); `nyc_dog_bites`\nhandles that lag internally rather than erroring or returning empty for\n\"this year\" queries early in a new year.\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"nyc-animals\": {\n      \"url\": \"https://gateway.pipeworx.io/nyc-animals/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/nyc-animals/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1558+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Standalone (no gateway account)\n\nThis package also runs as a local stdio MCP server — no Pipeworx account, no\ngateway round-trip:\n\n```json\n{\n  \"mcpServers\": {\n    \"nyc-animals\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@pipeworx/mcp-nyc-animals\"]\n    }\n  }\n}\n```\n\nOr run it directly to confirm it starts:\n\n```bash\nnpx -y @pipeworx/mcp-nyc-animals\n```\n\nIt speaks MCP over stdin/stdout and answers `initialize`/`tools/list`/`tools/call`\nfor **only** this pack's tools — none of the shared meta-tools the gateway\nconnection above adds. Same source, same tools, no ask_pipeworx routing.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Nyc Animals data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 4211,
  "sha": "8fc93fde49010279ed150bf369fc705a670adcb5bc56feac3488d8aff13fea66",
  "repo_slug": "pipeworx-io/mcp-nyc-animals",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_nyc_animals_894be114/readme"
}