Integration

tl;dv integration

tl;dv records online meetings (Google Meet, Zoom, Teams) and turns them into transcripts and AI notes. List and search meetings, read a meeting's details, its speaker-attributed transcript and its AI notes, get a short-lived download link for the recording, and import a recording from a public media URL. API access to a meeting depends on the plan of its organizer (Pro, Business or Enterprise; never Free) and the API is in alpha (v1alpha1). The beta multipart recording upload (enabled on request, needs byte-range PUTs to signed storage URLs) and the deprecated highlights route are not exposed. Authentication is a tl;dv API key (tldv.io app, Personal settings, API keys) sent in the x-api-key header.

Connect tl;dv How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in tl;dv.Built from the 7 tl;dv tools below, on the connection you add once.

What you can do with tl;dv

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.

Meeting, 2 operations

get_meetingGet meetingGETReturns one meeting: name, happenedAt, duration (seconds), its tl;dv url, organizer and invitees (names and emails, personal data), template, and the phoneNumber and metadata given when it was imported.
list_meetingsList meetingsGETLists the meetings the key's user can read through the API, paginated (page, limit up to 100), optionally filtered by search text, date range, participation or internal/external. Returns results[] with each meeting's id, name and date.

Download, 1 operation

get_recording_download_urlGet recording download urlGETReturns location, a signed URL to download the meeting's recording file. The URL expires 6 hours after it is issued; call again for a fresh one.

Health, 1 operation

check_healthCheck healthGETChecks that the tl;dv API is up: returns status ok. It does not check the API key or read any meeting.

Import, 1 operation

import_meetingImport meetingPOSTImports a recording into tl;dv from a public media URL and queues it for transcription; returns jobId. It creates a meeting (a MeetingReady webhook may fire). Set dryRun to true to validate without importing.

Note, 1 operation

get_meeting_notesGet meeting notesGETReturns the AI notes of a meeting: markdownContent (the whole notes as markdown), structuredNotes[] (each note's text, timestamp and topicId) and topics[] (title, summary and order).

Transcript, 1 operation

get_meeting_transcriptGet meeting transcriptGETReturns the speaker-attributed transcript of a meeting: data[] of sentences, each with speaker, text, startTime and endTime in seconds. Answers only once the transcript is complete.

Use tl;dv from Claude Code, Cursor or Codex

Connect tl;dv in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its tl;dv 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 tl;dv

Create your workspace
Sign up free. Nothing to install.
Connect tl;dv once
Add your tl;dv 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.