Bring Property Management
to Pydantic AI
Learn how to connect Mews to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the Mews MCP Server?
Connect your Mews hotel to any AI agent and transform your front desk into an intelligent, voice-ready concierge.
What you can do
- Reservations — Today's check-ins, upcoming arrivals, room assignments, and booking status
- Guests — Search profiles, loyalty tiers, preferences, allergies, and past stays
- Rooms — Real-time room status: vacant/occupied, housekeeping (clean/dirty/inspected)
- Billing — Guest folios, charges, payments, and balance tracking
- Rates & Services — Rate plans, bookable services, and POS outlet items
- Property — Hotel configuration, departments, and operational settings
Who is this for?
- Front Desk — "Who is checking in today? Any VIP arrivals?" — instant morning briefing
- Revenue Managers — Rate plan performance, occupancy trends, and ADR analysis
- Housekeeping — Room status dashboard, turnover priorities, and out-of-order tracking
- General Managers — Daily operational KPIs across all departments
Built-in capabilities (12)
Get guest profile
Get hotel configuration
Get reservation details
Filter by date range. THE core tool — "Who is checking in today?" "How many rooms tonight?" Get hotel reservations
Filter by guest for their complete financial history. List guest bills
With pricing and categories. List POS items
With amounts, dates, and settlement status. List payments
With pricing, restrictions, and availability rules. List room rates
With dates, room types, and release dates. List room blocks
List hotel rooms
List hotel services
Returns profile, contact info, nationality, loyalty status, past stays, preferences, and billing history. Search hotel guests
Why Pydantic AI?
Pydantic AI validates every Mews tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Mews integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Mews connection logic from agent behavior for testable, maintainable code
Mews in Pydantic AI
Mews and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Mews to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Mews in Pydantic AI
The Mews MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Mews for Pydantic AI
Every tool call from Pydantic AI to the Mews MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
What types of hotels use Mews?
Mews serves 5,000+ properties in 85+ countries — from boutique hotels and hostels to luxury resorts and hotel groups. It's a cloud-native PMS designed for modern hospitality.
Is the Mews API suitable for large hotel groups?
Yes, Mews provides a robust API that supports multi-property operations, making it ideal for hotel groups to manage central reservations, corporate billing, and group-wide reporting.
Can I check room housekeeping status in real-time?
Yes, you can query Mews to get the real-time status of any room, including whether it is clean, dirty, inspected, or out of order, which helps prioritize housekeeping efforts.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Mews MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai