How to Use the Robin MCP in Pydantic AI

Q: How does Pydantic AI validate Robin API responses?

The framework maps the output of tools like listdesks and getspace against strict Pydantic models at runtime. If the API returns unexpected fields, it raises a validation error immediately.

Q: How do I configure the Robin MCP Server in Pydantic AI?

You use the unified MCPToolset helper to connect your Pydantic AI agent to the external MCP server and pass it to your Agent constructor. This replaces the deprecated HTTP server imports and handles connection pooling.

Type-safe desk and room bookings for Pydantic AI agents with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Robin MCP to Pydantic AI

Create your Vinkius account to connect Robin to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Robin with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Type-safe office bookings with Pydantic AI

Stop worrying about your model sending malformed reservation requests when it uses `reserve_desk` to book a space. This MCP Server forces every response through strict runtime validation. When your agent calls `reserve_desk`, the framework validates the desk ID and date format before the API call even goes out. If the model tries to book an invalid space, the system fails loudly with a validation error. This prevents silent failures and keeps your reservation system clean, ensuring `book_space` only runs with correct, typed parameters.

Validated room discovery and scheduling

Finding a meeting room requires accurate data, which your agent gets by calling `list_spaces` to pull available rooms. The framework maps the JSON response directly to Pydantic models. You can then safely use `get_free_busy` to check calendar slots without worrying about missing fields or unexpected null values. To verify specific room setups, the agent calls `get_space`. Because Pydantic AI is model-agnostic, you can use this toolset with GPT-4o, Claude, or local models while maintaining the same strict data schemas.

Reliable desk cancellation and tracking

When plans change, your agent needs to clean up using `cancel_desk_reservation` to release desks. The framework ensures the reservation ID matches your exact type definitions, eliminating database mismatches. To keep track of office locations, the agent calls `list_locations` and `get_location`. This gives your system a structured, validated map of your physical offices, making it easy to build reliable automations for hybrid teams.

Setup guide

Set up Robin 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": {
        "robin-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Robin 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 Robin Workspace API. 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 Robin 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 Robin MCP in Pydantic AI

The framework maps the output of tools like `list_desks` and `get_space` against strict Pydantic models at runtime. If the API returns unexpected fields, it raises a validation error immediately.

Yes, Pydantic AI is model-agnostic, meaning you can hook up tools like `reserve_desk` and `book_space` to local models or commercial APIs seamlessly.

You use the unified `MCPToolset` helper to connect your Pydantic AI agent to the external MCP server and pass it to your `Agent` constructor. This replaces the deprecated HTTP server imports and handles connection pooling.

The framework will catch the error before sending it to the API. If the agent provides an invalid format to `reserve_desk`, the run loops back and prompts the model to correct the input.

All data passes through a secure, ephemeral V8 isolate sandbox hosted by the Vinkius MCP network. Your desk IDs, reservation timestamps, and employee info are never persisted or used for training.

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