How to Use the Robin MCP in Google ADK

Q: How do I add Robin MCP tools to my Google ADK agent?

You initialize McpToolset with the Vinkius HTTP URL and pass it to your LlmAgent. The Gemini model will automatically see tools like listspaces and bookspace in its tool declaration.

Q: How do I restrict which Robin tools Google ADK can access?

You can use the toolnames filter in the ADK setup to only expose specific tools like getlocation or listdesks, keeping booking actions restricted if needed.

Q: Does this toolset support hot-desk reservations?

Yes, the agent can call reservedesk for a specific date and location. It can also run canceldeskreservation if the employee is no longer coming into the office.

Connect Gemini models to your office layout using Google ADK to analyze space usage and automate bookings.

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 Google ADK

Create your Vinkius account to connect Robin to Google ADK — 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Enterprise space coordination with Google ADK

Give your Gemini agents the ability to map physical offices by calling `list_locations` to map out your corporate real estate. By loading this MCP Server into your toolset, the model uses `list_locations` to map out your corporate real estate. It pairs this with BigQuery data to analyze which offices are seeing the most foot traffic. When an employee needs a workspace, the agent runs `list_desks` to find what is open at that specific site. It then triggers `reserve_desk` to lock in the spot, keeping your physical workspace aligned with digital schedules.

Long-context meeting scheduling

Gemini's million-token context window lets you feed months of meeting data into the agent, using `list_space_events` to pull historical room usage. This allows the model to find patterns in how your teams collaborate. It can then recommend optimal times for recurring syncs. To book a room, the agent checks availability with `get_free_busy` across several candidate spaces. Once it finds a match, it calls `book_space` to finalize the calendar invite, handling the entire process inside your enterprise pipeline.

Granular resource management via MCP

Your agent can inspect specific room capabilities before making a decision by calling `get_space` to pull details like seating capacity and AV setup. This ensures your team does not end up in a phone booth for a ten-person board meeting. If a project gets pushed, the agent uses `cancel_desk_reservation` to release the desk back to the shared pool. This keeps your hot-desking system accurate and prevents real estate waste without requiring manual cleanup from facilities teams.

Setup guide

Set up Robin MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Robin tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Robin_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Robin tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You initialize `McpToolset` with the Vinkius HTTP URL and pass it to your `LlmAgent`. The Gemini model will automatically see tools like `list_spaces` and `book_space` in its tool declaration.

Yes, because the ADK integrates with your Google Cloud data, you can feed output from `list_space_events` into your model to run complex spatial analysis over large datasets.

You can use the `tool_names` filter in the ADK setup to only expose specific tools like `get_location` or `list_desks`, keeping booking actions restricted if needed.

Yes, the agent can call `reserve_desk` for a specific date and location. It can also run `cancel_desk_reservation` if the employee is no longer coming into the office.

Your location IDs and reservation records are processed entirely in a zero-trust, ephemeral V8 sandbox on the Vinkius MCP host. No data is cached or stored, ensuring your corporate physical security details never leak.

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