How to Use the LiveKit Real-Time Rooms MCP in OpenAI Agents SDK

Q: How do I query active sessions using LiveKit Real-Time Rooms and OpenAI Agents SDK?

Run listrooms to get an immediate list of every room currently running on the server. This tells you which calls are live, allowing your agent to route tasks correctly.

Q: Can I update session settings using LiveKit Real-Time Rooms and OpenAI Agents SDK?

Yeah, updateroommetadata is what you want. It lets you attach custom JSON data to the room object itself—think of it as attaching a mission status report right to the call.

Q: If I need participant info in LiveKit Real-Time Rooms and OpenAI Agents SDK, which tool do I use?

Just call getparticipant with the ID. It pulls all the detailed information about that specific user right away. You can then decide what your agent needs to act on.

Q: Does using LiveKit Real-Time Rooms and OpenAI Agents SDK require special permissions?

You need roomCreate permission if you want the server to spin up a new room for your agents. Otherwise, managing existing rooms is straightforward.

Manage LiveKit Real-Time Rooms actions directly from your OpenAI Agents SDK workflow.

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 OpenAI Agents SDK

Create your Vinkius account to connect LiveKit Real-Time Rooms to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control the MCP Server room state.

Use `create_room` to spin up a new live session, giving participants access via tokens. You can also run `delete_room` when the call is done, which cleans up everything and disconnects everyone. Need to know what's going on? `list_rooms` shows all active sessions right now, while `get_participant` grabs detailed info for a specific user.

Broadcast reliable messages via the MCP Server.

`send_data` lets you push a message to every person in the room. You decide if it's 'reliable'—meaning it gets there, guaranteed—or 'lossy,' which is better for low-latency data. Beyond simple chat, you can use `update_room_metadata` to stick structured JSON data to the session itself.

Manage participants in LiveKit Real-Time Rooms.

`remove_participant` handles kicking a user out of the room; it also revokes their token on LiveKit Cloud, which is smart. If you need to talk to one person, `list_participants` gets all names and IDs. You can fine-tune audio with `mute_track`. This tool lets your agent mute or unmute a specific participant's published video or voice feed.

Setup guide

Set up LiveKit Real-Time Rooms 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 LiveKit Real-Time Rooms tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LiveKit Real-Time Rooms 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="LiveKit Real-Time Rooms Agent",
            instructions="You have access to LiveKit Real-Time Rooms 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 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 OpenAI Agents SDK

Run `list_rooms` to get an immediate list of every room currently running on the server. This tells you which calls are live, allowing your agent to route tasks correctly.

Yeah, `update_room_metadata` is what you want. It lets you attach custom JSON data to the room object itself—think of it as attaching a mission status report right to the call.

Just call `get_participant` with the ID. It pulls all the detailed information about that specific user right away. You can then decide what your agent needs to act on.

You need `roomCreate` permission if you want the server to spin up a new room for your agents. Otherwise, managing existing rooms is straightforward.

The primary data handled includes participant metadata and structured JSON strings attached to the room object itself. These are non-sensitive, session management details.

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