How to Use the Ezus MCP in Pydantic AI

Q: How do I initialize the Ezus MCP Server in Pydantic AI?

Use the MCPToolset constructor with your Vinkius HTTP endpoint. Pass the toolset directly into your Agent instance to make all 12 tools available to your model.

Run type-safe Ezus travel integrations using Pydantic AI to validate every API response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ezus MCP to Pydantic AI

Create your Vinkius account to connect Ezus to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Ezus with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe client data validation

The `get_client` tool is the entry point for this MCP Server, pulling customer records into strict Pydantic models. Any missing email or malformed phone number triggers an immediate validation error. Using `list_clients`, your agent scans your entire database while enforcing your exact schema. This stops corrupted client profiles from breaking downstream booking systems.

Bulletproof invoice tracking

The `get_invoice` tool fetches detailed billing records and parses them against strict financial schemas. If a supplier sends a malformed invoice, the system catches it before processing. By using `list_invoices`, your agent monitors payments across all active trips. The runtime validation ensures that every price, tax rate, and total matches your accounting rules exactly.

Validated project updates

The `upsert_project` tool lets your agent write new travel itineraries back to your database with strict type safety. It ensures dates, budgets, and client IDs conform to your schema. The agent then calls `get_project` to confirm the write succeeded. This guarantees that your travel database never ends up with half-written or corrupted project files.

Setup guide

Set up Ezus MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "ezus-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Ezus tools.",
)

result = await agent.run("List recent Ezus transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Ezus. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Ezus now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Ezus MCP in Pydantic AI

Use the `MCPToolset` constructor with your Vinkius HTTP endpoint. Pass the toolset directly into your `Agent` instance to make all 12 tools available to your model.

The framework raises a validation error immediately. This prevents your agent from making decisions based on corrupted supplier or invoice data.

Yes. You can configure your agent to only call read-only tools like `list_products` and `get_supplier`, preventing any accidental writes to your database.

Yes. Because Pydantic AI is model-agnostic, you can test your travel agent workflows locally using open-source models before deploying to production.

All operations run in an isolated V8 sandbox on Vinkius. Your API keys are encrypted at rest and never exposed to the LLM, keeping your travel booking details safe from unauthorized access.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript