# Pet Data Station

> Source-verified pet food regulations, recalls, nutrient standards and species care data.

- name: com.petforai/pet-data-station
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 93/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.petforai%2Fpet-data-station
- tools: https://api.protogrid.dev/v1/servers/com.petforai%2Fpet-data-station/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "pet-data-station": {
      "type": "http",
      "url": "https://petforai.com/mcp/"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-77d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search_pet_recalls (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_pet_topics (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); submit_feedback (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,323 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 1,323 tokens to load them all
- tool set hash: eb49acf5d9f14fe58212037382f7b3b8
- badge: [![protogrid quality](https://protogrid.dev/badge/com.petforai/pet-data-station.svg)](https://protogrid.dev/servers/com.petforai/pet-data-station)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://petforai.com/mcp/ (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (8)

- `check_banned_breed`: Check banned / restricted dog-breed directories across jurisdictions
(UK + Northern Ireland + Scotland, Singapore, AU states, CN cities).

jurisdiction: 'UK'|'Beijing'|'NSW'|'Singapore'|'Queensland'|...
breed: 'pit bull'|'XL Bully'|'mastiff'|...  Returns breed lists per
jurisdiction + summary excerpt (full legal text via get_topic_context).
- `compare_nutrient_standards`: Compare one nutrient across 2-3 standards, e.g.
standards='AAFCO_2024,FEDIAF_2025' (bare codes 'AAFCO,FEDIAF' = latest
indexed edition). Other params as in get_nutrient_value.
- `get_ade_stats`: FDA animal-drug adverse-event (ADE) stats per active ingredient
(openFDA CVM report database, 68 compiled ingredients).

ingredient: active-ingredient name or substring, e.g. 'afoxolaner',
'carprofen', 'fluralaner'. species: optional filter, e.g. 'Dog', 'Cat',
'Horse' — restricts to ingredients reporting that species and returns
only that species' count. Returns structured summary stats (total
reports, species breakdown, top VEDDRA reactions) parsed from
C1-verified topics — report-level aggregates, not additive, not
causation. Full citation-rich text via get_topic_context(topic_id).
- `get_nutrient_value`: Single nutrient requirement from one standard. All 6 params required.

standard: AAFCO|FEDIAF|EU|GB|CFIA|KFDA|MAFF; year: edition year, e.g. 2024;
species: dog|cat; lifestage: adult|GR (growth & reproduction);
nutrient: protein|fat|calcium|taurine|... (aliases ok: Ca, P);
basis: DM (dry matter) | cal (per 1000 kcal ME).
- `get_topic_context`: Fetch one topic's RAG context (~200-500 tokens): source-verified claims
(verbatim for Open-Access / public-domain sources, paraphrased derived
summaries for copyrighted veterinary references) plus structured source
citations (authority/title/url) and a `trust` block (raw trust axes +
computed display_grade for this topic). Discover topic_ids with
search_pet_topics first.
- `search_pet_recalls`: Search pet-food recall / enforcement data (FDA + EU RASFF + CN enforcement).

brand: brand/product keyword, e.g. 'diamond'; reason: hazard keyword, e.g.
'salmonella', 'aflatoxin'; year: e.g. 2025. Returns summary excerpts
traceable via topic_id (full detail via get_topic_context).
- `search_pet_topics`: Search the source-verified pet regulatory & health topic whitelist.

Free-text over topic_id/title/category (tokenized AND). Returns metadata
only (anti-dump design) plus a `trust` block per result (raw trust axes
authority_tier/fidelity/license + computed display_grade, see server
instructions); follow up with get_topic_context(topic_id) for
the full citation-rich text. category is an optional exact filter, e.g.
'aafco', 'evidence', 'ade', 'vaccine-guidelines'.
- `submit_feedback`: Leave feedback for the station's human maintainers (2026-08-16).

type: 'data_request' (data you could not find — the most valuable signal),
'error_report' (a claim that mismatches its cited source; include topic_id),
'knowledge_lead' (a fact worth adding; source_url REQUIRED — first-hand
sources only: statutes, government datasets, peer-reviewed papers).
One-way mailbox: stored for human review, never publicly rendered, never
auto-ingested — every published topic stays C1 source-verified.
Cap: 10 submissions/day per agent.