tl;dv MCP Server

Meetings, transcripts, notes, clips and sharing for your tl;dv account.

托管 MCP 服务器

npx add-mcp 'https://cotlet.dev/mcp/v1/tldv'

可安装到 Claude Code、Codex、Cursor 等客户端

文档

Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up

tl;dv API and MCP server: Let your AI agent tidy up your tl;dv library.

tl;dv runs its own MCP server in the Claude and ChatGPT connector directories and has a REST API in version v1alpha1 (checked 27 Oct 2026). Both need Pro or higher, and both read meetings, transcripts and notes; the README of the official server says it "cannot create, edit, delete, or share meetings". Cotlet runs 13 tl;dv tools hosted, 7 of them writes, over MCP for agents and REST for scripts.

Meetings, transcripts, notes, clips and sharing for your tl;dv account. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.

MCP setup REST API guide

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by tl;dv. tl;dv is a trademark of its owner. If tl;dv's own integrations cover what you need, use them first.

What can you automate in tl;dv?

  • Share recordings with the right people
  • Clip budget and objection moments
  • Pin quotes as timestamped notes
  • Rename "Quick sync" calls
  • File calls in customer folders
  • Collect the week's action items

Does tl;dv have an MCP server or an API?

  • A meeting is reachable through the official MCP server or API only if its organizer is on Pro or higher. tl;dv's API article says sharing a meeting with you "does not grant API export permissions".
  • The only writes in the official API import or upload a new recording. Zapier has 3 triggers (note, transcript, recording added) and 1 action, Upload Recording. Webhooks send MeetingReady and TranscriptReady.
  • A search on the official MCP server returns up to 50 meetings and, by default, only calls you took part in.
What you needOfficial tl;dv MCPtl;dv API, ZapierCotlet
Search meetings, read transcripts and notesYes, 50 per searchYesYes
Share a meeting or close a public linkNoNoYes, after your OK
Cut clips and add timestamped notesNoNoYes
Rename meetings and file them in foldersNoNoYes
Meetings organized by someone on FreeNoNoYes, if you can open them
Plan you needPro or higherPro or BusinessYour current plan

Checked 27 Oct 2026. Sources: tl;dv MCP server, official repository, tl;dv Help: MCP, tl;dv Help: API, tl;dv Help: Webhooks, tl;dv on Zapier, tl;dv pricing

How does Cotlet connect to tl;dv?

  1. Sign in to tl;dv. Use your own account in its Cotlet Cloud Browser.
  2. Choose MCP or REST. Connect your agent or create a Cotlet API key.
  3. Run your workflow. Ask your agent or send an HTTP request.

We never keep your tl;dv password, and no share or public link that emails someone or opens a call to them is saved before you approve it.

Connect tl;dv to your agent or workflow

Use MCP with your AI agent, or HTTP requests in n8n, Make, Zapier and scripts. Follow the MCP setup below or jump to the REST guide.

  1. Sign in to tl;dv in a Cloud Browser. Create a Cotlet account, open tl;dv in its Cloud Browser, sign in the way you always do (Google, Microsoft or email, with your SSO or 2-step check) and press Enable for agents.
  2. Add the Cotlet address. Put https://cotlet.dev/mcp/v1 into the MCP server or connector settings of your agent.
  3. Approve the connection. Chat apps send you to a Cotlet sign-in page. Code editors, n8n and scripts take an API key from the console.

https://cotlet.dev/mcp/v1 carries every app you enable on Cotlet, tl;dv with them. If you can already reach tl;dv's own read-only connector, both can sit side by side; refresh the Cotlet connector after you enable tl;dv so its tools show up.

Claude:

Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect

Claude Code:
claude mcp add --transport http cotlet \
  https://cotlet.dev/mcp/v1 \
  --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT:

Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth

Cursor:

// ~/.cursor/mcp.json
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": { "Authorization": "Bearer ${env:COTLET_API_KEY}" }
    }
  }
}

Codex:

# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"

n8n:

MCP Client Tool (inside an AI Agent)
Transport: HTTP Streamable
URL: https://cotlet.dev/mcp/v1
Auth: Bearer, <your key>
Tool: tldv_read

Make, Zapier:

Make: MCP Client > Call a tool
Zapier: MCP Client by Zapier > Run Tool
Server URL: https://cotlet.dev/mcp/v1
Token: <your key>
Tool: tldv_write

How to use the tl;dv REST API

Create your Cotlet API key

Create a Cotlet API key with access to tl;dv and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.

Connect tl;dv in Cotlet and enable it for agents. Account access: Your own tl;dv account. What your agent can do follows your role on each meeting (Admin, Editor or Viewer). You sign in once in your own Cloud Browser and keep your SSO or 2-step verification.

Make your first tl;dv API request

REST:

curl "https://cotlet.dev/api/v1/tldv/meetings?limit=50" \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read meetings and apply the operation limits

A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.

Illustrative response excerpt:

{
  "status": "success",
  "app": "tldv",
  "tool": "list_meetings",
  "result": {
    "meetings": [
      {
        "meeting_id": "mt_4f21a9",
        "title": "Acme discovery call",
        "started_at": "2026-10-15T14:00:00Z",
        "duration_minutes": 42,
        "organizer": "You",
        "role": "admin",
        "participants": 3,
        "folder": null,
        "status": "ready"
      }
    ],
    "next_cursor": "eyJvZmZzZXQiOjUwfQ"
  }
}

Lists meetings in your tl;dv library, newest first. Filter by a text query, a date range or a folder.

Each item shows your role on the meeting (admin, editor or viewer), which decides what you can change. Pages hold up to 50 meetings; pass next_cursor back as cursor for the next page.

A meeting still being processed shows status processing.

from: Only meetings on or after this date.

to: Only meetings on or before this date.

limit: 1 to 50. Default: 20.

cursor: Next page cursor from the previous call.

Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.

tl;dv workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestFull transcript of a meeting with speaker and time per line. Use get_transcript in your configured workspace report.
MakeHTTP > Make a requestAI notes grouped by topic, plus the notes people added by hand, with timestamps. Use get_meeting_notes in your configured workspace report.
Python or Node.jsREST APIClips in your Clips library with title, meeting and length, newest first. Use list_clips in your configured workspace report.

Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.

Cotlet reads tl;dv; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.

Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.

The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.

tl;dv API endpoints and MCP tools

Meetings, transcripts and notes

Up to 50 meetings a page, with your role on each. A recording tl;dv still processes comes back as processing, with no text yet.

  • List meetings (list_meetings, read): Meetings in your library with title, date, duration, your role and folder, newest first.
  • Get meeting (get_meeting, read): One meeting with participants, link, folder and who can open it.
  • Get transcript (get_transcript, read): Full transcript of a meeting with speaker and time per line.
  • Get meeting notes (get_meeting_notes, read): AI notes grouped by topic, plus the notes people added by hand, with timestamps.

Clips and notes

A clip shares nothing until you send its link, and a note added after the call sends no Slack mention.

  • List clips (list_clips, read): Clips in your Clips library with title, meeting and length, newest first.
  • Create clip (create_clip, write): Save a segment of a meeting as a clip in your Clips library.
  • Add note (add_note, write): Add a timestamped note to a finished meeting, under your name.

Names and folders

Filing needs Editor or Admin on the meeting, and only new version folders take meetings.

  • Rename meeting (rename_meeting, write): Change the title of a meeting.
  • List folders (list_folders, read): Your folders with who can open them, version and number of meetings.
  • Add meeting to folder (add_to_folder, write, asks first): File a meeting in one of your folders. Needs the Editor or Admin role on the meeting.

Sharing and deleting

Each person added gets an email from tl;dv. A deleted recording cannot be recovered.

  • Share meeting (share_meeting, write, asks first): Give people or a whole domain access to a meeting. Needs the Admin or Editor role on the meeting.
  • Set link access (set_link_access, write, asks first): Make a meeting public to anyone with the link, or limit it to the people with access.
  • Delete meeting (delete_meeting, write, asks first): Permanently delete a recording. It cannot be recovered.

Inputs, REST path and example response of every tool: https://cotlet.dev/integrations/tldv-api-mcp-server#tools

Who can see my tl;dv session, and how do I revoke it?

  • What we store. Your signed-in tl;dv profile, AES-256-GCM, in Finland. No password, no tl;dv API key.
  • What your agent gets. 13 tl;dv tools. No cookie, no login, no download link to the video.
  • What the session sees. Every meeting your tl;dv user can open, with what customers said on the call.
  • What no tool touches. The recording bot, calendar sync, recording rules, integrations and billing.
  • If tl;dv signs you out. We email you a link to sign in again. You do it yourself, we never do.
  • How to cut access. Disable for agents, reset the browser or delete the key. The next call fails.

Transcripts carry what other people said, so ask before you send a customer call to an agent. tl;dv's own MCP server and API are in its SOC 2 program and pentest scope. Cotlet has A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).

Approvals, undo and mistakes

  1. Lists the day's calls. Skips any recording tl;dv still processes, for the next run.
  2. Reads who has access. The access list and link level of each call, and your role on it.
  3. Waits for your OK. Each share waits in your Cotlet console with the addresses tl;dv will email.
  4. Reports back. Shared, skipped, public links still on, and calls where you are only a Viewer.
ActionUndo
Share a meetingRemove the person; the invite email already went out
Make a link publicset_link_access back; anyone who opened it has seen it
Add a noteEdit or delete it from the note's menu
Rename a meetingRename it back; the old title comes in the response
Delete a recordingNo, tl;dv keeps no backups

4 of the 7 write tools ask first: sharing, public links, filing in a folder others can open, and deleting. create_clip, add_note and rename_meeting run at once, since a clip, a note or a title reaches nobody by email. Reads run at once. For a scheduled run you can switch the wait off per tool.

A domain share such as *@acme.io reaches everyone at that company who signs in, not only the people on the call.

MCP call:

{
  "name": "share_meeting",
  "arguments": {
    "meeting_id": "mt_4f21a9",
    "share_with": [
      "dana@acme.io",
      "sam@acme.io"
    ],
    "access": "viewer"
  }
}

REST:

curl -X POST https://cotlet.dev/api/v1/tldv/meetings/mt_4f21a9/share \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"share_with":["dana@acme.io","sam@acme.io"],"access":"viewer"}'

Response:

{
  "meeting_id": "mt_4f21a9",
  "shared_with": [
    {
      "who": "dana@acme.io",
      "access": "viewer"
    },
    {
      "who": "sam@acme.io",
      "access": "viewer"
    }
  ],
  "notified": 2
}

A script that runs after each call can use the same tools over REST at /api/v1/tldv, with one key and one price. A call your tl;dv role does not allow, such as sharing a meeting where you are a Viewer, returns an error and costs nothing. Every tool row above lists its REST path.

How much does the tl;dv MCP server cost?

About $32 a month for one person who records about 15 calls a week, 5,470 credits. tl;dv Pro is EUR 29 a seat a month, or EUR 18 billed yearly.

JobCallsCredits
Share new recordings by your rule, each workday6 × 221,320
Clip and note key moments, per customer call5 × 261,300
Rename and file the week's calls14 × 4560
Action items from the week's notes18 × 4720
Delete old test recordings, monthly7 × 170
Cloud Browser, 30 days1,500
Total5,470
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • No tl;dv API key or Pro organizer needed

The month is our example: about 15 recorded calls a week, 6 of them with customers, shared each workday, clipped after each customer call, filed weekly. tl;dv publishes no average per user; surveys put office workers at 10 to 15 meetings a week, and Pro allows 80 recordings. Dollars at the $29 pack rate.

tl;dv MCP server on GitHub, Zapier or hosted: which to use

OptionWhat it doesWhere it stops
tldv-public/tldv-mcp-servertl;dv's own local build: search, metadata, transcript, notes. 15 stars, last commit 29 Sep 2026.Needs a Pro API key; tl;dv says it does not update it regularly. No license.
Composio tl;dv toolkitHosted, 7 tools on the API: list, get, transcript, highlights, download, import.Reads and imports only, on your API key.
AnythingMCP guideSelf-hosted MCP with 6 tools on TLDV_API_KEY.Same API, so no share, clip, note or folder.
vagarylabs/tldv_downloaderPython script that downloads recordings on a session token. 20 stars, MIT.Downloads only; no MCP.
Zapier3 triggers when a note, transcript or recording is added; 1 action, Upload Recording.Sends data out; changes nothing in tl;dv.

If you only want to ask questions about your calls and you are on Pro, tl;dv's own connector does that for free. If new transcripts should land in a CRM, Zapier or webhooks cover it. If the agent should share, clip, note, rename and file, Cotlet does that hosted.

Also listed on: Odel, mcpbeat

Who runs Cotlet

Behind Cotlet is Take Group sp. z o.o., a software company registered in Poland, EU (VAT PL6342984273), working since 2019. The founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Questions about the tl;dv tools go to contact@cotlet.dev.

tl;dv API and MCP: questions

How do I get access?

Sign up free at https://cotlet.dev, open tl;dv under Integrations in the console and sign in to tl;dv in its Cloud Browser. The trial starts when you sign up and needs no card.

How do I connect tl;dv to ChatGPT or Claude?

Sign up at cotlet.dev, log in to tl;dv once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your tl;dv account through Cotlet, in their phone apps too.

What can ChatGPT do in tl;dv?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in tl;dv: share new recordings with the right people; turn key moments in calls into clips and notes; rename meetings and file them in folders. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need a paid tl;dv plan or an API key?

No key. Cotlet works in your own tl;dv account, so what your agent can do follows your role on each meeting: changing sharing needs admin or editor, and filing in a folder needs Editor or Admin. tl;dv's own API and MCP server are different: they need an organizer on a paid plan, and the MCP server needs Pro or higher.

Can my agent send the tl;dv bot to a meeting?

No. Cotlet's tools work on recordings that already exist. tl;dv's help center adds the bot through the Chrome extension or the desktop app, or by turning on auto-recording in Preferences, and neither tl;dv's API nor its MCP server sends the bot.

Does tl;dv have webhooks?

Yes, on Pro and Business: MeetingReady and TranscriptReady, per user, team or organization. Cotlet sends no events of its own. Point a webhook at your script and let it call the Cotlet tools, or run your agent on a schedule.

Does it work on the tl;dv Free plan?

Yes, the tools work in your own account on any plan. Free keeps its own limits: AI notes only on the first 10 meetings, so get_meeting_notes may come back empty for later calls, and 40 recordings a week.

Can I use it next to tl;dv's own MCP server?

Yes. They do not touch each other. You can ask questions through the official connector and let Cotlet do the shares, clips and folders.

Is the MCP server different from the REST API?

Only in how you call it. Both have the same 13 tools, inputs and answers, one API key and one price. Agents use MCP; scripts and webhook handlers use REST.

Is Cotlet affiliated with tl;dv?

No. Cotlet is independent and not affiliated with tl;dv or tldx Solutions GmbH.

Can I use the tl;dv API without an AI agent?

Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.


Give your AI agents your signed-in browser.

Product: Integrations · How it works · Pricing · Security

Resources: Blog · API docs · Help center · Changelog · GitHub

Solutions: For developers · For automation agencies

Company: About · AI info: company facts · Contact

Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors

Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.