How to Use the LiveKit Real-Time Rooms MCP in Google ADK

Q: How do I programmatically start a LiveKit Real-Time Room using Google ADK?

To begin, call createroom. This action sets up the virtual environment needed for your agents to run their logic against. It's step one before any data exchange.

Q: Can I read session details in LiveKit Real-Time Rooms using Google ADK?

Yes, listrooms provides an overview of all active rooms, and getparticipant lets you deep dive into specific user metrics. This is vital for auditing sessions.

Q: What's the best way to handle participant changes in LiveKit Real-Time Rooms using Google ADK?

You use removeparticipant when a user needs to leave, and listparticipants if you just need a current count. Both tools keep your BigQuery records accurate.

Q: Does the MCP Server support updating room context for LiveKit Real-Time Rooms and Google ADK?

Absolutely. Use updateroommetadata to attach structured JSON data, letting you pass complex state information that your agents need for reasoning.

Control LiveKit Real-Time Rooms actions with your Google ADK enterprise agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiveKit Real-Time Rooms MCP to Google ADK

Create your Vinkius account to connect LiveKit Real-Time Rooms to Google ADK 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 LiveKit Real-Time Rooms with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage the lifecycle of a LiveKit Real-Time Room via MCP Server.

`create_room` starts a new session, and `delete_room` cleans it up completely when your work is done. You can also use `list_rooms` to check which sessions are still active. This makes sure your agent knows exactly when a call started or ended, letting you handle the state transitions reliably within BigQuery workflows.

Send specific data messages across LiveKit Real-Time Rooms.

`send_data` broadcasts information to everyone in the room. You'll specify if that message needs 'reliable' delivery or if low latency is more important, selecting between 'lossy' and 'reliable'. It’s great for feeding real-time operational data directly into your agent pipeline.

Monitor and adjust participant status using the MCP Server.

`list_participants` gives you a full roster of who's in the room. If someone leaves, `remove_participant` handles that cleanly. You can also use `get_participant` to pull specific details about any user. Need to manage the audio feed? `mute_track` lets your agent toggle mute status for precise session control.

Setup guide

Set up LiveKit Real-Time Rooms 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 LiveKit Real-Time Rooms 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="LiveKit Real-Time Rooms_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LiveKit Real-Time Rooms 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 LiveKit. 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 LiveKit Real-Time Rooms 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 LiveKit Real-Time Rooms MCP in Google ADK

To begin, call `create_room`. This action sets up the virtual environment needed for your agents to run their logic against. It's step one before any data exchange.

Yes, `list_rooms` provides an overview of all active rooms, and `get_participant` lets you deep dive into specific user metrics. This is vital for auditing sessions.

You use `remove_participant` when a user needs to leave, and `list_participants` if you just need a current count. Both tools keep your BigQuery records accurate.

Absolutely. Use `update_room_metadata` to attach structured JSON data, letting you pass complex state information that your agents need for reasoning.

The server manages participant metadata and room metadata. These are structured JSON strings, allowing you to attach operational context to the session records.

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