How to Use the LiveKit MCP in Vercel AI SDK

Q: Can the Vercel AI SDK handle LiveKit session metadata?

Yes. You can use updateroommetadata to push changes to the server whenever your agent needs to annotate a session. The changes propagate to all connected clients immediately.

Use the Vercel AI SDK to control LiveKit rooms and egress jobs directly from your React or Next.js interface.

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 Vercel AI SDK

Create your Vinkius account to connect LiveKit to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time room management via AI SDK

Trigger `create_room` or `remove_participant` actions instantly as your AI client processes user intent. The streamable response pattern ensures your frontend updates the state before the user even notices a delay. You avoid the overhead of manual API calls by mapping these tools into your `generateText` or `streamText` functions. Everything stays inside your existing TypeScript workflow.

Automated egress control for Vercel AI SDK

Start recording sessions with `start_room_composite_egress` or `start_track_composite_egress` through your AI client. You get a direct link to the recorded assets as soon as the job finishes. This keeps your media pipelines contained within the same logic that handles your application state. Your users see the recording status update live on their screen without needing a refresh.

SIP and trunk configuration

Manage your telephony infrastructure by calling `create_sip_inbound_trunk` or `create_sip_outbound_trunk` within your AI agent's logic. You can provision phone numbers for your LiveKit setup without leaving your IDE. It handles the heavy lifting of mapping calls to specific rooms. You simply define the dispatch rules and let the agent handle the rest of the configuration.

Setup guide

Set up LiveKit MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all LiveKit tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent LiveKit transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install the MCP client package and configure your transport to point at your Vinkius endpoint. Once initialized, pass the tool definitions into your agent to enable direct interaction.

Yes. You can use `update_room_metadata` to push changes to the server whenever your agent needs to annotate a session. The changes propagate to all connected clients immediately.

Vinkius handles all the auth tokens for you. Your agent only interacts with the MCP server through a secure, ephemeral tunnel that prevents unauthorized access to your media streams.

The server returns an error code through the tool execution. You can catch this in your TypeScript code and trigger a fallback or alert the user immediately.

No. The server only processes room configurations, participant lists, and egress requests. Your actual video and audio data never touch the AI client's storage or memory.

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