Integration

LiveKit integration

Real-time audio and video communication platform. Create rooms, manage participants, handle recordings, and control media streams. Perfect for video conferencing, live streaming, webinars, and real-time collaboration applications.

Connect LiveKit How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in LiveKit.Built from the 14 LiveKit tools below, on the connection you add once.

Common LiveKit use cases

Moderation
Recording
Room state
End meetings
Chat messages
End recording
OBS streaming
Start meetings
Role management
Room management

What you can do with LiveKit

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Participant, 4 operations

get_participantGet participantPOSTRetrieves details about a specific participant.
list_participantsList participantsPOSTRetrieves all participants in a room.
remove_participantRemove participantPOSTRemoves a participant from a room.
update_participantUpdate participantPOSTUpdates a participant's permissions and metadata.

Room, 4 operations

create_roomCreate roomPOSTCreates a new video/audio room.
delete_roomDelete roomPOSTCloses and deletes a room.
list_roomsList roomsPOSTRetrieves all active video/audio rooms.
update_room_metadataUpdate room metadataPOSTUpdates room metadata.

Egress, 3 operations

list_egressList egressPOSTLists active and recent egress processes.
start_room_composite_egressStart room composite egressPOSTStarts recording or streaming of a room.
stop_egressStop egressPOSTStops an active recording or stream.

Data message, 1 operation

send_dataSend dataPOSTSends data message to room participants.

Ingress, 1 operation

create_ingressCreate ingressPOSTCreates an RTMP or WHIP ingress endpoint.

Track, 1 operation

mute_published_trackMute published trackPOSTMutes or unmutes a participant's audio/video track.

Use LiveKit from Claude Code, Cursor or Codex

Connect LiveKit in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its LiveKit operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect LiveKit

Create your workspace
Sign up free. Nothing to install.
Connect LiveKit once
Add your LiveKit connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

LiveKit integration FAQ

What can you do with the LiveKit integration?

LiveContext exposes 14 operations on LiveKit, covering participant, room, egress and data message. Common uses include Moderation, Recording and Room state.