How to Use the Robin MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system prevent double-bookings in Robin?

Yes, you can use the SDK guardrails alongside getfreebusy to verify room availability before running bookspace. This prevents the agent from triggering conflicting reservations.

Q: How do I handle agent handoffs when using Robin with OpenAI Agents SDK?

You can define one agent for location discovery using listlocations and another for booking. The SDK lets them hand off context so the booking agent can execute reservedesk with the correct ID.

Q: What happens if a reservation needs to be deleted?

The agent calls canceldeskreservation using the specific reservation ID. This immediately updates the workplace platform so other employees can see the desk is open.

Let your OpenAI Agents SDK system manage physical desk bookings and meeting rooms without manual API integrations.

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 OpenAI Agents SDK

Create your Vinkius account to connect Robin to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Securely book office assets with OpenAI Agents SDK

Your agent can inspect floor plans and lock down space instantly using `list_desks` to check what is open, then runs `reserve_desk` to secure a spot for the day. You don't have to write custom validation logic because the SDK handles the tool discovery out of the box. If a user needs a larger room, the agent coordinates with `list_spaces` and executes `book_space`. The built-in guardrails in this Python framework ensure that the agent never books a room outside of allowed business hours or double-books an existing reservation.

Coordinate team calendars with an MCP Server

Stop checking three different schedules to find a joint meeting time; instead, use `get_free_busy` to scan several room schedules at once. The agent runs on Vinkius, which means your agent connects to the Robin MCP server securely using a single endpoint token. When plans change, the agent uses `cancel_desk_reservation` to clean up the workspace inventory. This keeps your office data clean and prevents empty desks from sitting idle when someone decides to work from home.

Multi-agent handoffs for office logistics

You can set up one agent to find locations using `list_locations` and hand off the task to a booking agent. The booking agent then calls `get_space` to verify room resources like projectors or whiteboards before finalizing the reservation. OpenAI's tracing dashboard lets you watch this entire handoff happen in real time. By using the `list_space_events` tool, the system can cross-reference physical room usage against digital invites. This ensures your teams actually show up to the rooms they reserved, automatically freeing up spaces when meetings end early.

Setup guide

Set up Robin MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Robin tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Robin tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Robin tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Robin Agent",
            instructions="You have access to Robin tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You install the SDK, spin up the MCP server via Vinkius, and pass the server parameter to your agent constructor. The agent automatically discovers tools like `list_desks` and `reserve_desk` so you can start managing office spaces in code immediately.

Yes, you can use the SDK guardrails alongside `get_free_busy` to verify room availability before running `book_space`. This prevents the agent from triggering conflicting reservations.

You can define one agent for location discovery using `list_locations` and another for booking. The SDK lets them hand off context so the booking agent can execute `reserve_desk` with the correct ID.

The agent calls `cancel_desk_reservation` using the specific reservation ID. This immediately updates the workplace platform so other employees can see the desk is open.

Vinkius runs the MCP server in an isolated V8 sandbox, meaning your desk IDs and reservation details are never stored. The connection uses ephemeral execution, so your API tokens and office layouts remain completely private.

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