ezyVet MCP
MCP server for ezyVet veterinary practice management. Enables reading and creating animals, contacts, appointments, consults, and invoices via natural language.
README
ezyVet MCP
Model Context Protocol (MCP) server for ezyVet — cloud-based veterinary practice management software.
Talk to ezyVet from Claude, Cursor, or any MCP client. Read animals (patients), contacts (owners), appointments, consults, invoices. Create new records. Tokens are OAuth2 client-credentials with 12-hour TTL, auto-refreshed.
Built against the ezyVet REST API. No existing MCP for ezyVet — this is the first.
What you can do with it
You: "Find dog 'Rex' for owner Sarah Johnson and show upcoming appointments."
Claude: *find_contacts + find_animals + find_appointments → summary*
You: "Book a vaccination appointment for animal 4523 next Tuesday at 10am."
Claude: *list_appointment_types, then create_appointment with right type_id*
You: "Open a new consult for the cat we just saw — note the diagnosis."
Claude: *create_consult with animal_id, vet_id, notes*
You: "What invoices does contact 892 have from this month?"
Claude: *find_invoices with contact_id + date range*
Install
pip install -e .
Configure
Register as an ezyVet integration partner to get your credentials.
export EZYVET_PARTNER_ID="..."
export EZYVET_CLIENT_ID="..."
export EZYVET_CLIENT_SECRET="..."
export EZYVET_SITE_UID="..."
export EZYVET_SCOPE="read-animal read-contact read-appointment read-consult read-invoice read-user"
Use with Claude Desktop
{
"mcpServers": {
"ezyvet_mcp": {
"command": "ezyvet_mcp",
"env": {
"EZYVET_PARTNER_ID": "...",
"EZYVET_CLIENT_ID": "...",
"EZYVET_CLIENT_SECRET": "...",
"EZYVET_SITE_UID": "...",
"EZYVET_SCOPE": "..."
}
}
}
}
Tools
| Tool | Type | What it does |
|---|---|---|
health_check |
Diagnostic | Mints a token + lists users |
get_animal |
Read | Single animal (patient) |
find_animals |
Read | Search animals |
create_animal |
Write | New patient |
update_animal |
Write | Patch patient fields |
get_contact |
Read | Single contact (owner) |
find_contacts |
Read | Search owners |
create_contact |
Write | New owner |
find_appointments |
Read | List appointments |
create_appointment |
Write | Book appointment |
find_consults |
Read | List visits |
create_consult |
Write | Open visit |
find_invoices |
Read | List invoices |
list_species |
Read | Reference: species |
list_breeds |
Read | Reference: breeds |
list_appointment_types |
Read | Reference: appointment types |
list_users |
Read | Reference: practice staff |
API coverage
Maps MCP tools to ezyVet's 216-endpoint REST API. Full docs: https://developers.ezyvet.com/
Rate limits
ezyVet throttles most endpoints at 60 req/min and globally at 180 req/min per database. The client auto-retries 401s (token refresh) but doesn't retry 429s — slow down on your end if you hit them.
Development
pip install -e ".[dev]"
pytest
ezyvet_mcp
Need a custom MCP for your SaaS?
I build production-grade MCP servers for vertical SaaS — insurance, dental, veterinary, legal, property mgmt, home services. Typical engagement: 2-4 weeks, $25K-$120K. Source-owned, MIT-licensed, no vendor lock-in.
See sanjibani/mcp-services or email sanjibani@users.noreply.github.com.
Ships in the sanjibani vertical-MCP portfolio — see also hawksoft-mcp, open-dental-mcp, ezyvet-mcp, jobber-mcp, paid-skills, mcp-vertical-template.
MIT.
Acknowledgements
- ezyVet for the public REST API + OAuth flow
- Built using mcp-vertical-template
- Inspired by sanjibani/hawksoft-mcp and sanjibani/open-dental-mcp (same template pattern)
See also
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。