How to Use the LiveKit MCP in Cursor

Q: How do I configure Cursor to talk to my LiveKit MCP Server?

Create a .cursor/mcp.json file in your project root and add the LiveKit server configuration. Enable Agent mode in the chat panel, and the editor will immediately recognize the WebRTC tools.

Q: Can Cursor trigger LiveKit recordings while I am debugging?

Yes, you can ask the Cursor agent to run starttrackcompositeegress to record a specific audio and video track together. This helps you verify that your recording pipelines work while you edit the layout code.

Q: How does the Cursor agent handle LiveKit SIP trunk setup?

The editor can call createsipinboundtrunk to provision telephony infrastructure while you are writing your routing backend. This lets you test inbound phone calls against your local workspace.

Q: Can I send data packets to WebRTC clients from Cursor?

Yes, you can use senddata to broadcast custom payload packets to active room participants. This is incredibly useful for testing custom chat or signaling features directly from your editor.

Write real-time video code and test LiveKit API calls directly inside your Cursor editor with Agent mode.

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 Cursor

Create your Vinkius account to connect LiveKit to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug live LiveKit sessions inside the Cursor editor

`list_rooms` fetches active WebRTC sessions directly into your Cursor chat so you can inspect live production states. Instead of jumping to a web dashboard, your MCP agent pulls real-time room data right into your workspace. You can use `get_participant` to check connection states while you are writing client-side joining logic. This means you can write your React components using actual, live participant payloads instead of static mock files.

Provision RTMP and WHIP endpoints inside Cursor

`create_ingress` generates RTMP, WHIP, or URL pull entry points directly from your Cursor MCP agent prompt. When building live-streaming features, you can generate these endpoints instantly to test your ingestion pipelines. If your streaming setup changes, the agent can run `update_ingress` to modify participant permissions or room targets. This keeps your local development flow fast since you don't have to manually configure ingest tokens.

Control audio and video tracks via Cursor Agent

`mute_published_track` allows Cursor's Agent mode to silence specific media feeds via the MCP Server during active testing sessions. You can write your moderation backend while testing the actual API behavior in real-time. The agent can also execute `update_subscriptions` to change which tracks a developer is subscribing to. This makes it easy to debug bandwidth issues right from the editor sidebar.

Setup guide

Set up LiveKit MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the LiveKit MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent LiveKit transactions." If the MCP tools are loaded correctly, Cursor will call the LiveKit tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "livekit-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Create a `.cursor/mcp.json` file in your project root and add the LiveKit server configuration. Enable Agent mode in the chat panel, and the editor will immediately recognize the WebRTC tools.

Yes, you can ask the Cursor agent to run `start_track_composite_egress` to record a specific audio and video track together. This helps you verify that your recording pipelines work while you edit the layout code.

The editor can call `create_sip_inbound_trunk` to provision telephony infrastructure while you are writing your routing backend. This lets you test inbound phone calls against your local workspace.

Yes, you can use `send_data` to broadcast custom payload packets to active room participants. This is incredibly useful for testing custom chat or signaling features directly from your editor.

No, Cursor only accesses API metadata such as participant lists, room names, and SIP configurations. Your actual media packets are routed directly through your LiveKit server and never pass through the editor.

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