Otter.ai MCP Server

Meeting transcripts, highlights and sharing in Otter, by your agent.

Hosted MCP Server

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

Installs into Claude Code, Codex, Cursor and more

Documentation

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

Otter.ai API and MCP server: Let your AI agent do the follow-up after every Otter call.

Yes, Otter.ai runs an official MCP server at mcp.otter.ai with three read-only tools (search, fetch, user info) on every plan, and a REST API for Enterprise workspaces whose only write imports a file (checked 27 Oct 2026). Neither can share a conversation, add a highlight or change an action item. Cotlet runs 15 Otter.ai tools hosted, over MCP for agents and REST for scripts, on the plan you already have.

Meeting transcripts, highlights and sharing in Otter, by your agent. 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 Otter.ai. Otter.ai is a trademark of its owner. If Otter.ai's own integrations cover what you need, use them first.

What can you automate in Otter.ai?

  • Share notes with call attendees
  • Round up and close action items
  • Highlight decisions for a recap
  • Answer questions from old calls
  • Import recordings from other tools
  • Export transcripts as DOCX, PDF or SRT

Does Otter.ai have an MCP server or an API?

  • The REST API has 7 operations: channels, channel members, conversations, one conversation, its audio, the workspace and an import from a file URL. Keys need an Enterprise workspace, 2 per user.
  • Workspace webhooks send each finished conversation with summary, action items and who it is shared with, also Enterprise only.
  • Zapier has one trigger (New Recording) and one action (import a recording), from Pro.
What you needOfficial Otter MCPOtter API (Enterprise)Cotlet
Search and read transcriptsYesYesYes
List action itemsNo toolPer conversationAcross all calls
Share or unshare a conversationNoReads the list onlyYes, after your OK
Highlights, complete or reassign itemsNoNoYes
Import a recordingNoFrom a file URLFrom a file URL, after your OK
Export DOCX, PDF, SRT or a bulk ZIPNoText and MP3 onlyYes, per your plan
Plan you needAny, Basic tooEnterpriseAny

Checked 27 Oct 2026. Sources: Otter Help: Otter MCP Server, Otter Help: Otter.ai Public API, Otter Help: Workspace Webhooks, Otter Help: Connect Otter to Zapier, Otter.ai pricing

How does Cotlet connect to Otter.ai?

  1. Sign in to Otter.ai. 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 Otter.ai password, and nobody gets access to a conversation until you approve the share.

Connect Otter.ai 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 Otter.ai in a Cloud Browser. Create a Cotlet account, open Otter.ai in its Cloud Browser, sign in with Google, Microsoft or your Otter email on any plan, then press Enable for agents.
  2. Add the Cotlet address. Paste https://cotlet.dev/mcp/v1 into the MCP server or connector settings of your agent.
  3. Allow the connection. Chat apps show a Cotlet sign-in page once. Code editors, n8n and scripts send an API key from the console.

https://cotlet.dev/mcp/v1 serves every app you enable on Cotlet, Otter.ai included. Otter's own server at mcp.otter.ai can stay connected next to it; if you enable Otter.ai on Cotlet later, refresh the connector so the new 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: otter_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: otter_write

How to use the Otter.ai REST API

Create your Cotlet API key

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

Connect Otter.ai in Cotlet and enable it for agents. Account access: Your own Otter.ai account (any plan; bulk export needs Business or Enterprise).

Make your first Otter.ai API request

REST:

curl "https://cotlet.dev/api/v1/otter/conversations?limit=20" \
  -H "Authorization: Bearer $COTLET_API_KEY"

Read conversations 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": "otter",
  "tool": "list_conversations",
  "result": {
    "conversations": [
      {
        "conversation_id": "cv_7f3a91",
        "title": "Pricing review with Acme",
        "owner": "you@example.com",
        "created_at": "2026-10-13T14:00:00Z",
        "summary": "The team compared per-seat and flat-rate pricing and agreed to send a revised quote.",
        "shared": true
      },
      {
        "conversation_id": "cv_2b84d0",
        "title": "Onboarding kickoff",
        "owner": "you@example.com",
        "created_at": "2026-10-14T09:30:00Z",
        "summary": null,
        "shared": false
      }
    ],
    "next_cursor": "eyJvZmZzZXQiOjIwfQ"
  }
}

Lists conversations you own, most recent first, the same order as My Conversations. Set include_shared to add conversations shared with you, or pass channel_id to list one Channel, which includes shared ones.

The summary is Otter's generated summary and is empty while processing is still running. Pass next_cursor back as cursor for the next page.

limit: Page size. 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.

Otter.ai workflows for agents and automations

ToolConnect throughExample workflow
n8nHTTP RequestFull transcript of a conversation as text with speaker names and optional timestamps. Use get_transcript in your configured workspace report.
MakeHTTP > Make a requestAction items assigned to you across all conversations, or all items of one conversation. Use list_action_items in your configured workspace report.
Python or Node.jsREST APIHighlights and comments in a conversation, in the order they appear. Use list_highlights 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 Otter.ai; 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.

Otter.ai API endpoints and MCP tools

Conversations and transcripts

Reads cover your own conversations and the ones shared with you, Channels included. A transcript holds every speaker's words, so treat it as theirs too.

  • List conversations (list_conversations, read): Your Otter conversations, most recent first, with title, owner, date and summary.
  • Search transcripts (search_transcripts, read): Meetings whose transcripts match a phrase, with date and the matching passage.
  • Get conversation (get_conversation, read): One conversation with summary, owner, who it is shared with and processing status.
  • Get transcript (get_transcript, read): Full transcript of a conversation as text with speaker names and optional timestamps.
  • List channels (list_channels, read): Channels you belong to with owner, member count and visibility.

Sharing

Viewer is the default. A Collaborator can edit, export and share further if the owner allows it, so the agent gives it only to people you name.

  • Share conversation (share_conversation, write, asks first): Share a conversation with people by email or with a Channel, as Viewer or Collaborator.
  • Unshare conversation (unshare_conversation, write, asks first): Remove a person or a Channel from the sharing list of a conversation.

Action items and highlights

Your Action Items tab shows only items assigned to you; pass a conversation to see everyone's. Deleting an item in Otter cannot be undone, so no tool deletes.

  • List action items (list_action_items, read): Action items assigned to you across all conversations, or all items of one conversation.
  • Complete action item (complete_action_item, write): Check an action item off, or reopen it.
  • Assign action item (assign_action_item, write, asks first): Reassign an action item to another user.
  • List highlights (list_highlights, read): Highlights and comments in a conversation, in the order they appear.
  • Add highlight (add_highlight, write): Highlight a passage of a transcript, or remove an existing highlight.

Import and export

Basic exports TXT only and allows 3 imports for the life of the account. Bulk export needs Business or Enterprise, and Otter emails the ZIP link.

  • Import audio or video (import_audio, write, asks first): Import an audio or video file from a URL for transcription, summary and action items.
  • Export conversation (export_conversation, read): Export a conversation as TXT, DOCX, PDF or SRT, or its audio as MP3, and return a download link.
  • Bulk export conversations (bulk_export_conversations, read): Export many conversations as one ZIP. Otter emails you the download link. Business and Enterprise plans.

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

Who can see my Otter.ai session, and how do I revoke it?

  • What we store. Your signed-in Otter.ai profile, encrypted with AES-256-GCM, in Finland. Never the password.
  • What your agent gets. 15 Otter.ai tools. No cookie, no login, no audio player.
  • What the session sees. Your conversations, the ones shared with you and your Channels. Nothing from colleagues' private notes.
  • What no tool touches. Deleting conversations, billing, workspace admin settings, the Notetaker and auto-share rules.
  • If Otter signs you out. We email you a sign-in link. You sign in and type any 2FA code yourself.
  • How to cut access. Disable for agents, reset the browser or delete the key. The next call fails.

With 2FA on, Otter asks for a code once per device; the Cloud Browser stays that one device until you sign out. The Cotlet site has A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory (live results).

Approvals, undo and mistakes

  1. Finds the day's calls. Most recent first, stopping at the first conversation older than today.
  2. Waits for the summary. A call still processing is left for the next run, so no one opens an empty page.
  3. Waits for your OK. Each share sits in your Cotlet console with the names, the permission and anyone outside your domain.
  4. Reports back. Who got access, who already had it, and the calls left for you.
ActionUndo
Share a conversationunshare_conversation; Otter's share email may already be in their inbox
Add a highlightadd_highlight with remove set to true
Complete an action itemcomplete_action_item with completed set to false
Reassign an action itemOnly the new assignee, or you inside the conversation, can hand it back
Import a recordingDelete the conversation in Otter; on Basic it still counts toward the month

4 of the 6 write tools ask first. add_highlight and complete_action_item run at once: both are undone with one call and send nothing to anyone, though people who can open the conversation see the highlight. Reads and exports run at once. For a scheduled run you can switch the wait off per tool.

An import uses your transcription minutes and, on Pro, one of 10 imports a month. The agent never retries an import it cannot confirm failed.

MCP call:

{
  "name": "add_highlight",
  "arguments": {
    "conversation_id": "cv_7f3a91",
    "text": "We decided to go with the flat-rate option for the pilot."
  }
}

REST:

curl -X POST https://cotlet.dev/api/v1/otter/conversations/cv_7f3a91/highlights \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"We decided to go with the flat-rate option for the pilot."}'

Response:

{
  "conversation_id": "cv_7f3a91",
  "highlight_id": "hl_31",
  "timestamp": "12:41",
  "text": "We decided to go with the flat-rate option for the pilot.",
  "removed": false
}

A cron job or a CRM sync can call the same tools over REST at /api/v1/otter, with one key and one price and no Enterprise plan. A call your Otter user cannot make, such as a DOCX export on Basic, returns the reason and costs nothing. Every tool row above lists its REST path.

How much does the Otter.ai MCP server cost?

About $26 a month for one account manager with about 15 calls a week, 4,510 credits. Works on any Otter plan; Pro is $16.99 a user a month, or $8.33 billed yearly.

JobCallsCredits
Share the day's customer calls with attendees6 × 221,320
Questions about past calls3 × 20600
Weekly decisions recap with highlights11 × 4440
Friday action item roundup7 × 4280
Import outside recordings4 × 8320
Monthly bulk export to an archive5 × 150
Cloud Browser, 30 days1,500
Total4,510
  • Free 7-day trial, no card
  • 10 credits per successful call, MCP or REST
  • 50 credits a day for the Cloud Browser
  • No Otter Enterprise plan or API key needed

The month is our example: shares after 22 workdays, 20 questions about old calls, a weekly recap and roundup, 8 imported recordings and one archive. Otter publishes no per-user meeting count; its own 2022 survey found 17.7 meetings a week for US employees. Dollars at the $29 pack rate.

Otter.ai MCP server on GitHub, official or hosted: which to use

OptionWhat it doesWhere it stops
gmchad/otterai-apiUnofficial Python library on Otter's web API: list, upload, download, trash. 92 stars, last commit 21 Oct 2026.A library, not an MCP server; your password in an env file; no sharing or action items.
DarrenZal/otter-mcpMCP server with search and transcript fetch. 5 stars, last commit 22 Jan 2026.Reads only, which the official server already does.
StanAngeloff/otter-mcpMCP server built because the official one hides some shared conversations. 1 star, last commit 11 Jun 2026.Three reads; needs your password and TOTP secret on your computer; no license.
ChocoTonic/otterai-mcpMCP server that lists folders and moves conversations into them. 0 stars, last commit 21 Oct 2026.Folders only.

If you only ask questions about your meetings, Otter's free official server is enough. If you run an Enterprise workspace and build your own sync, use the API and webhooks. If your agent should share notes, close and reassign action items, highlight, import and export, Cotlet does that hosted, on any plan.

Also listed on: Odel, mcpbeat

Who runs Cotlet

Take Group sp. z o.o. runs Cotlet: a software company registered in Poland, EU (VAT PL6342984273), in business since 2019. The founders are Bart Krawczyk (Co-founder, CTO) and Jake Slugocki (Co-founder, SEO, sales and marketing). Write to contact@cotlet.dev with questions about the Otter.ai tools.

Otter.ai API and MCP: questions

How do I get access?

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

How do I connect Otter.ai to ChatGPT or Claude?

Sign up at cotlet.dev, log in to Otter.ai 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 Otter.ai account through Cotlet, in their phone apps too.

What can ChatGPT do in Otter.ai?

With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Otter.ai: share meeting notes with attendees after a call; collect action items from all meetings; import call recordings for transcription. You ask in plain words, and anything that reaches other people waits for your OK first.

Do I need an Enterprise plan or an Otter API key?

No. Cotlet works in your own Otter account and does not use the public API, which Otter makes available to Enterprise workspaces only. What a tool can do still follows your plan: bulk export needs Business or Enterprise, and the Basic free plan limits imports and exports to TXT.

Can I use Otter's official MCP server together with Cotlet?

Yes. The official server reads (user info, search, fetch a transcript) and connects by OAuth in Claude, ChatGPT or Cursor. Cotlet adds what it lacks: sharing, highlights, action item changes, imports and exports. Use search_transcripts and get_transcript on either side.

Can my agent join or record meetings?

No. Recording stays with Otter's Notetaker and your calendar settings. The tools work on conversations that already exist, or on a recording you import by link.

Does it work on the Basic free plan?

Yes, within Basic's limits: 300 transcription minutes a month, 3 imports for the life of the account and TXT export only. Sharing, highlights and action items work on every plan.

Is the MCP server different from the REST API?

Only in how you call it. Both have the same 15 tools, inputs and answers, with one API key and one price. Agents use MCP; scripts and CRM syncs use REST.

Is Cotlet affiliated with Otter.ai?

No. Cotlet is independent and not affiliated with Otter.ai, Inc.

Can I use the Otter.ai 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.