How to Use the LiveKit MCP in OpenAI Agents SDK

Q: How do I connect LiveKit to my OpenAI Agents SDK pipeline?

Install the SDK with pip install openai-agents and initialize the MCP connection using MCPServerStreamableHttp. Pass the configured server inside the mcpservers list when instantiating your agent.

Q: How does the OpenAI Agents SDK optimize tool calls for LiveKit?

Set cacheToolsList=True in your configuration to avoid fetching the MCP schema on every single turn. This speeds up response times when the agent needs to call listparticipants or updateparticipant during high-traffic sessions.

Q: Can I record specific web layouts using this setup?

You can trigger web-based recordings by calling startwebegress through your agent. This spins up a headless browser to capture any URL, which you can modify on the fly using updatelayout.

Run production-grade voice and video rooms with OpenAI Agents SDK using secure, auto-discovered LiveKit tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiveKit MCP to OpenAI Agents SDK

Create your Vinkius account to connect LiveKit 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Room Management with OpenAI Agents SDK

The `create_room` tool lets your agent spin up real-time communication spaces on demand based on user activity. When a session ends, the agent cleans up the infrastructure by invoking `delete_room` to force-disconnect remaining users. You don't need to write custom API wrappers for your Python services. This MCP Server exposes these actions directly to your agent, which handles room lifecycles while maintaining strict schema validation.

Granular Participant and Track Control

The `mute_published_track` tool gives your agent the power to moderate live sessions by silencing specific audio or video feeds. If a user violates room rules, the agent uses `remove_participant` to eject them instantly from the active call. To keep tracks organized, the agent calls `update_subscriptions` to manage which participant receives which media stream. This keeps bandwidth usage low and ensures users only download the tracks they actually need.

High-Fidelity Session Recording and Egress

Using this MCP Server, the `start_room_composite_egress` tool triggers a server-side recording of the entire room using a custom web layout. For more granular post-production needs, your agent can initiate `start_track_composite_egress` to capture individual audio and video tracks separately. Managing active recordings is handled through `stop_egress` when the session concludes. Your agent tracks ongoing jobs using `list_egress`, ensuring no recording runs longer than necessary.

Setup guide

Set up LiveKit 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 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LiveKit 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 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 Agent",
            instructions="You have access to LiveKit 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 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 MCP in OpenAI Agents SDK

Install the SDK with `pip install openai-agents` and initialize the MCP connection using `MCPServerStreamableHttp`. Pass the configured server inside the `mcp_servers` list when instantiating your agent.

Yes, your agent can monitor active sessions and take immediate action. It uses tools like `mute_published_track` and `remove_participant` to enforce your platform's community guidelines automatically.

Set `cacheToolsList=True` in your configuration to avoid fetching the MCP schema on every single turn. This speeds up response times when the agent needs to call `list_participants` or `update_participant` during high-traffic sessions.

You can trigger web-based recordings by calling `start_web_egress` through your agent. This spins up a headless browser to capture any URL, which you can modify on the fly using `update_layout`.

No, Vinkius runs in a zero-trust, ephemeral V8 Isolate Sandbox that never retains your API keys, room metadata, or participant details. All data packets processed via `send_data` pass through the MCP Server memory without touching persistent storage.

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