How to Use the LiveKit MCP in Mastra AI

Q: How do I monitor LiveKit usage in Mastra AI?

Use listrooms and listparticipants to get the current status of your infrastructure. Your agent can summarize this data and report back to your dashboard.

Build complex media workflows in Mastra AI by automating LiveKit room creation and SIP routing.

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 Mastra AI

Create your Vinkius account to connect LiveKit to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Workflow-driven LiveKit room orchestration

Chain together `create_room` and `create_sip_participant` to build automated call sequences. Mastra AI manages the state and retries if a network blip interrupts your connection. You define the logic once and let the agent handle the execution. If a participant fails to join, the agent can trigger a retry or notify an admin automatically.

Granular egress control for Mastra AI

Manage long-running sessions by using `start_track_composite_egress` and `stop_egress` within your agent's workflow. This gives you precise control over which parts of a session get recorded for later review. It works perfectly for multi-step agents that need to record specific segments of a meeting. You can even update the layout mid-stream using `update_layout`.

SIP dispatch and phone management

Automate your telephony setup with `create_sip_dispatch_rule` and `purchase_phone_number` calls. Your agent can provision new numbers based on your specific campaign needs without manual intervention. This keeps your infrastructure code clean and version-controlled. Each step is logged and trackable within your agent's execution history.

Setup guide

Set up LiveKit MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All LiveKit tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "livekit-mcp-client",
  servers: {
    "livekit-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "LiveKit Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to LiveKit tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent LiveKit transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI uses its built-in workflow engine to catch errors from any tool call. You can define specific retry logic for `create_room` or any other server action.

Yes. Enable tool approval in your client config so an admin must sign off before the agent executes sensitive actions like `delete_room` or `remove_participant`.

It is. The MCP server provides the necessary interface for your agents to manage production-grade media infrastructure reliably.

Use `list_rooms` and `list_participants` to get the current status of your infrastructure. Your agent can summarize this data and report back to your dashboard.

Your participant IDs and metadata stay within the encrypted session. The agent only handles the necessary identifiers to perform its tasks.

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