Can I list all active rooms on my LiveKit server?

Yes! Use the `list_rooms` tool. It calls the LiveKit RoomService ListRooms endpoint and returns all currently open rooms with their participant count, metadata, and creation time.

How do I mute a participant's microphone?

First use `list_participants` to get the track SID for the participant's audio track. Then call `mute_track` with the room name, participant identity, track SID, and muted set to 'true'.

Does this work with self-hosted LiveKit servers?

Yes! Just provide your self-hosted server's URL (e.g., https://livekit.yourserver.com) as the Host URL, along with the API Key and Secret from your server's config.yaml.

LiveKit Real-Time Rooms MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: LiveKit Real-Time Rooms
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect LiveKit Real-Time Rooms through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="LiveKit Real-Time Rooms Assistant",
            instructions=(
                "You help users interact with LiveKit Real-Time Rooms. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from LiveKit Real-Time Rooms"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About LiveKit Real-Time Rooms MCP Server

Connect your AI agents to LiveKit, the open-source framework and cloud platform for real-time voice, video, and AI agent communication. This MCP provides 10 tools to manage the full room lifecycle via the LiveKit Twirp Room Service API.

The OpenAI Agents SDK auto-discovers all 10 tools from LiveKit Real-Time Rooms through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries LiveKit Real-Time Rooms, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Room Management — Create, list, and delete real-time voice/video rooms with configurable timeouts and participant limits
Participant Control — List, inspect, update metadata, and remove participants from active rooms
Track Moderation — Mute or unmute any published audio/video track for content moderation
Live Data Messaging — Broadcast data payloads to all participants with reliable or lossy delivery modes
Room Metadata — Dynamically update room-level metadata visible to all connected clients

The LiveKit Real-Time Rooms MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect LiveKit Real-Time Rooms to OpenAI Agents SDK via MCP

Follow these steps to integrate the LiveKit Real-Time Rooms MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from LiveKit Real-Time Rooms

Why Use OpenAI Agents SDK with the LiveKit Real-Time Rooms MCP Server

OpenAI Agents SDK provides unique advantages when paired with LiveKit Real-Time Rooms through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

LiveKit Real-Time Rooms + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the LiveKit Real-Time Rooms MCP Server delivers measurable value.

Automated workflows: build agents that query LiveKit Real-Time Rooms, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries LiveKit Real-Time Rooms, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through LiveKit Real-Time Rooms tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query LiveKit Real-Time Rooms to resolve tickets, look up records, and update statuses without human intervention

LiveKit Real-Time Rooms MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect LiveKit Real-Time Rooms to OpenAI Agents SDK via MCP:

create_room

Participants can join it via access tokens. Create a new LiveKit room with specified settings

delete_room

Requires roomCreate permission. Delete a room, disconnecting all participants

get_participant

Get detailed information about a specific participant

list_participants

List all participants currently in a room

list_rooms

List all active rooms on the LiveKit server

mute_track

Mute or unmute a participant's published track

remove_participant

On LiveKit Cloud, their token is also revoked. Remove a participant from a room

send_data

Use "reliable" for guaranteed delivery or "lossy" for low-latency. Send a data message to all participants in a room

update_participant_metadata

Update a participant's metadata

update_room_metadata

Use JSON strings for structured data. Update the metadata of a room

Example Prompts for LiveKit Real-Time Rooms in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with LiveKit Real-Time Rooms immediately.

"List all active rooms on my LiveKit server."

"Create a room called 'interview-session' with a max of 3 participants."

"Remove the participant 'user-abc' from room 'support-call-42'."

Troubleshooting LiveKit Real-Time Rooms MCP Server with OpenAI Agents SDK

Common issues when connecting LiveKit Real-Time Rooms to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

LiveKit Real-Time Rooms + OpenAI Agents SDK FAQ

Common questions about integrating LiveKit Real-Time Rooms MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.