Pet Data Station
Source-verified pet food regulations, recalls, nutrient standards and species care data.
我该使用它吗
质量与安全性
发现(1)
- LOW在 get_nutrient_value 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"pet-data-station": {
"url": "https://petforai.com/mcp/"
}
}
}远程端点
https://petforai.com/mcp/streamable-http它能做什么
工具清单
工具(8)
🟢search_pet_topics(q, category, limit)
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'.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string"
},
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"limit": {
"default": 10,
"type": "integer"
}
},
"required": [
"q"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟡submit_feedback(type, message, topic_id, source_url, agent)
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.
输入模式
{
"type": "object",
"properties": {
"type": {
"type": "string"
},
"message": {
"type": "string"
},
"topic_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"source_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"agent": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
}
},
"required": [
"type",
"message"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢get_topic_context(topic_id)
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.
输入模式
{
"type": "object",
"properties": {
"topic_id": {
"type": "string"
}
},
"required": [
"topic_id"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢get_nutrient_value(standard, year, species, lifestage, nutrient, ...)
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).
输入模式
{
"type": "object",
"properties": {
"standard": {
"type": "string"
},
"year": {
"type": "integer"
},
"species": {
"type": "string"
},
"lifestage": {
"type": "string"
},
"nutrient": {
"type": "string"
},
"basis": {
"type": "string"
}
},
"required": [
"standard",
"year",
"species",
"lifestage",
"nutrient",
"basis"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢compare_nutrient_standards(standards, species, lifestage, nutrient, basis)
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.
输入模式
{
"type": "object",
"properties": {
"standards": {
"type": "string"
},
"species": {
"type": "string"
},
"lifestage": {
"type": "string"
},
"nutrient": {
"type": "string"
},
"basis": {
"type": "string"
}
},
"required": [
"standards",
"species",
"lifestage",
"nutrient",
"basis"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢search_pet_recalls(brand, reason, year, limit)
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).
输入模式
{
"type": "object",
"properties": {
"brand": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"reason": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"year": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null
},
"limit": {
"default": 10,
"type": "integer"
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢get_ade_stats(ingredient, species, limit)
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).
输入模式
{
"type": "object",
"properties": {
"ingredient": {
"type": "string"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"limit": {
"default": 10,
"type": "integer"
}
},
"required": [
"ingredient"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}🟢check_banned_breed(jurisdiction, breed, limit)
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).
输入模式
{
"type": "object",
"properties": {
"jurisdiction": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"breed": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null
},
"limit": {
"default": 10,
"type": "integer"
}
},
"additionalProperties": false
}输出模式
{
"type": "object",
"additionalProperties": true
}社区
证据