[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Otter.ai API and MCP server

> Yes, but narrowly (checked 16 Oct 2026). Otter.ai has an official hosted MCP server with three tools (user info, search, fetch) that only read, and a public REST API available to Enterprise workspaces that reads conversations, transcripts, action items, insights, outlines, audio, channels and the workspace, and imports a recording from a file URL. Neither shares a conversation, adds a highlight or changes an action item.

AI meeting assistant that records and transcribes calls, then writes a summary, an outline and action items you can search, highlight and share with your team.

## What is the Otter.ai API?

Cotlet's Otter.ai API exposes 15 endpoints for your own Otter.ai account: list conversations, search transcripts, get conversation, get transcript, list highlights, list action items, list channels, export conversation, bulk export conversations, share conversation, unshare conversation, add highlight, complete action item, assign action item and import audio or video. The list_conversations endpoint returns your Otter conversations, most recent first, with title, owner, date and summary. Each endpoint takes simple JSON inputs like conversation_id, channel_id or limit and works both as an operation of the otter_read or otter_write MCP tool for agents and as a REST call for scripts.

- **Category:** [Productivity & teams](https://cotlet.dev/integrations/category/productivity-teams.md)
- **Endpoints:** 15 (9 read, 6 write)
- **Updated:** 2026-10-22

Yes, but narrowly (checked 16 Oct 2026). Cotlet is a hosted MCP server and REST API for Otter.ai with 15 endpoints (9 read, 6 write): you sign in once in your own cloud browser, your AI agent does the work.

## Does Otter.ai have an official API?

Yes, but narrowly (checked 16 Oct 2026). Otter.ai has an official hosted MCP server with three tools (user info, search, fetch) that only read, and a public REST API available to Enterprise workspaces that reads conversations, transcripts, action items, insights, outlines, audio, channels and the workspace, and imports a recording from a file URL. Neither shares a conversation, adds a highlight or changes an action item.

| Task | Otter.ai official | Cotlet |
|---|---|---|
| Search meeting transcripts | Yes: Official MCP search tool, read-only | Yes |
| Read a full transcript | Yes: Official MCP fetch tool; the public API returns it too, Enterprise only | Yes |
| List action items | Partly: The public API returns them per conversation, Enterprise only; the MCP has no tool for them | Yes |
| Share a conversation with people or a channel | No: The API shows who a conversation is shared with but cannot change it | Yes |
| Add or remove a highlight | No | Yes |
| Complete or reassign an action item | No | Yes |
| Import an audio or video file | Partly: The public API imports from a file URL, Enterprise only; Otter's Zapier action does the same | Yes |
| Export a transcript as DOCX, PDF or SRT, or audio as MP3 | Partly: The public API returns transcript text and an MP3 link, Enterprise only; no DOCX, PDF, SRT or bulk ZIP | Yes |

Sources: [Otter Help: Otter MCP Server](https://help.otter.ai/hc/en-us/articles/35287607569687-Otter-MCP-Server), [Otter Help: Otter.ai Public API](https://help.otter.ai/hc/en-us/articles/36130822688279-Otter-ai-Public-API), [Otter Help: Share a conversation](https://help.otter.ai/hc/en-us/articles/360048338793-Share-a-conversation), [Otter Help: Import recordings automatically using Zapier](https://help.otter.ai/hc/en-us/articles/34529576232215-Import-recordings-automatically-to-Otter-using-Zapier)

## For AI agents

```text
Yes, but narrowly (checked 16 Oct 2026). Otter.ai has an official hosted MCP server with three tools (user info, search, fetch) that only read, and a public REST API available to Enterprise workspaces that reads conversations, transcripts, action items, insights, outlines, audio, channels and the workspace, and imports a recording from a file URL. Neither shares a conversation, adds a highlight or changes an action item.
Cotlet provides a hosted MCP server and REST API for Otter.ai: 15 tools (9 read, 6 write).
Access       Sign up at https://cotlet.dev/app/signup?app=otter, then request the app and create API keys in the Cotlet console.

MCP server   https://cotlet.dev/mcp/v1
MCP tools    otter_read, otter_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base    https://cotlet.dev/api/v1/otter, each operation at its own route, e.g. POST /api/v1/otter/conversations/{conversation_id}/highlights
Auth         Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations   list_conversations, search_transcripts, get_conversation, get_transcript, list_highlights, list_action_items, list_channels, export_conversation, bulk_export_conversations, share_conversation, unshare_conversation, add_highlight, complete_action_item, assign_action_item, import_audio
Confirm      share_conversation, unshare_conversation, assign_action_item, import_audio (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown     https://cotlet.dev/integrations/otter-api-mcp-server.md

How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=otter, requests Otter.ai in the Cotlet console and creates an API key there.
2. The user signs in to Otter.ai once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Otter.ai for agents. An agent cannot do this step.
3. The API key goes into the MCP client or the REST call as a bearer token.

Fits: people who want a hosted Otter.ai server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Otter.ai MCP server instead.

Policy: Cotlet never stores passwords, never solves CAPTCHAs, never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Otter.ai in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Otter.ai only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Otter.ai login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Otter.ai's terms; Cotlet is not affiliated with Otter.ai.
```

## What can an AI agent do in Otter.ai?

Cotlet is best for teams on Otter.ai who want their AI agent to share notes, close action items, import recordings and export transcripts without running or fixing a server.

- **[Share meeting notes with attendees after a call](https://cotlet.dev/integrations/otter-api-mcp-server/share-meeting-notes-with-attendees.md)**: "After each customer call today, share the Otter conversation with the attendees as viewers and tell me who got access. Skip anyone who already has it." → `list_conversations`, `get_conversation`, `share_conversation`
- **[Collect action items from all meetings](https://cotlet.dev/integrations/otter-api-mcp-server/weekly-action-items-roundup.md)** (runs: weekly): "Every Friday, list my open Otter action items from this week's meetings, grouped by meeting, and mark the ones I tell you are done." → `list_action_items`, `get_conversation`, `complete_action_item`, `assign_action_item`
- **[Import call recordings for transcription](https://cotlet.dev/integrations/otter-api-mcp-server/import-recordings-for-transcription.md)**: "Import this recording into Otter as "Discovery call 14 Oct", wait until the transcript is ready, then give me the summary and the action items." → `import_audio`, `get_conversation`, `list_action_items`
- **Highlight decisions and pull them into a recap** (runs: weekly): "Search this week's Otter conversations for "we decided", highlight each decision and give me a one-page recap of the highlights." → `search_transcripts`, `get_transcript`, `add_highlight`, `list_highlights`
- **Archive transcripts as files each month** (runs: weekly): "Export last month's Otter conversations as DOCX with speaker names and timestamps, and email me the ZIP." → `list_conversations`, `export_conversation`, `bulk_export_conversations`

## Can Otter.ai automations run on a schedule in n8n, Make or Zapier?

Yes. Cotlet does not replace your automation platform: it gives it a Otter.ai connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to collect action items from all meetings, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.

| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/otter/action-items. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/otter/action-items with your API key. | cron or GitHub Actions. |

## Tools

**For AI agents:** Every endpoint and its schema is public. The 15 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Otter.ai.

### list_conversations

Your Otter conversations, most recent first, with title, owner, date and summary. Access: read. REST: `GET /api/v1/otter/conversations`. MCP: `otter_read → list_conversations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `include_shared` | boolean | no | Also list conversations shared with you. Default: false. |
| `channel_id` | string | no | Only conversations in this Channel, from list_channels. |
| `limit` | integer | no | Page size. Default: 20. |
| `cursor` | string | no | Next page cursor from the previous call. |

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.

Example response:

```json
{
  "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"
}
```

### search_transcripts

Meetings whose transcripts match a phrase, with date and the matching passage. Access: read. REST: `GET /api/v1/otter/transcripts/search`. MCP: `otter_read → search_transcripts`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `query` | string | yes | Words or a phrase to find. |
| `limit` | integer | no | Page size. Default: 20. |
| `cursor` | string | no | Next page cursor from the previous call. |

Searches the transcripts of every conversation you can open, including conversations shared with you, across all dates. Each result carries the conversation ID, the date and the passage that matched, so you can decide what to open with get_transcript. Results are ranked by match, not by date. A transcript holds what every participant said, so treat its content as theirs too.

Example response:

```json
{
  "results": [
    {
      "conversation_id": "cv_7f3a91",
      "title": "Pricing review with Acme",
      "created_at": "2026-10-13T14:00:00Z",
      "passage": "Sam Lee 12:41: We decided to go with the flat-rate option for the pilot."
    }
  ],
  "next_cursor": null
}
```

### get_conversation

One conversation with summary, owner, who it is shared with and processing status. Access: read. REST: `GET /api/v1/otter/conversations/{conversation_id}`. MCP: `otter_read → get_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |

Returns one conversation: title, owner, date, the generated summary, the people and Channels it is shared with and their permission, and whether the summary, action items and outline are finished. Use the status to wait for processing after an import or a new call. The transcript is a separate call, get_transcript.

Example response:

```json
{
  "conversation_id": "cv_7f3a91",
  "title": "Pricing review with Acme",
  "owner": "you@example.com",
  "created_at": "2026-10-13T14:00:00Z",
  "url": "https://otter.ai/u/example-conversation",
  "summary": "The team compared per-seat and flat-rate pricing and agreed to send a revised quote.",
  "shared_with": [
    {
      "email": "sam@example.com",
      "permission": "viewer"
    }
  ],
  "shared_channels": [],
  "processing": {
    "summary": "finished",
    "action_items": "finished",
    "outline": "finished"
  }
}
```

### get_transcript

Full transcript of a conversation as text with speaker names and optional timestamps. Access: read. REST: `GET /api/v1/otter/conversations/{conversation_id}/transcript`. MCP: `otter_read → get_transcript`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |
| `include_timestamps` | boolean | no | Add a timestamp to each paragraph. Default: true. |

Returns the whole transcript as plain text, one paragraph per speaker turn, in the order spoken. Timestamps are on by default; switch them off for shorter text. The call works for conversations you own and for ones shared with you. A transcript holds what every participant said, so treat its content as theirs too.

Example response:

```json
{
  "conversation_id": "cv_7f3a91",
  "format": "txt",
  "content": "Sam Lee  00:00\nThanks for joining. Let's start with the two pricing options.\n\nJane Doe  00:09\nWe prefer a flat rate if it keeps approvals simple.\n\nSam Lee  00:18\nUnderstood, I'll send a revised quote this week."
}
```

### list_highlights

Highlights and comments in a conversation, in the order they appear. Access: read. REST: `GET /api/v1/otter/conversations/{conversation_id}/highlights`. MCP: `otter_read → list_highlights`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |

Returns the highlighted passages and comments of one conversation in transcript order, each with its timestamp. The result is empty for a conversation with no highlights or comments. This is the same content as Otter's Highlights and Comments export.

Example response:

```json
{
  "highlights": [
    {
      "highlight_id": "hl_31",
      "timestamp": "12:41",
      "text": "We decided to go with the flat-rate option for the pilot.",
      "comment": null
    }
  ]
}
```

### list_action_items

Action items assigned to you across all conversations, or all items of one conversation. Access: read. REST: `GET /api/v1/otter/action-items`. MCP: `otter_read → list_action_items`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | no | Only items of this conversation, including items assigned to others. |
| `status` | enum | no | open, completed or all. Default: open. |
| `limit` | integer | no | Page size. Default: 50. |
| `cursor` | string | no | Next page cursor from the previous call. |

Without conversation_id, returns the items assigned to you across all your conversations, the same set as the Action Items tab, each with the conversation it came from. With conversation_id, returns every item of that conversation with its assignee. Status filters open or completed items. Pass next_cursor back as cursor for the next page.

Example response:

```json
{
  "action_items": [
    {
      "action_item_id": "ai_204",
      "text": "Send revised quote by Wednesday",
      "assignee": "you@example.com",
      "completed": false,
      "conversation_id": "cv_7f3a91",
      "conversation_title": "Pricing review with Acme"
    }
  ],
  "next_cursor": null
}
```

### list_channels

Channels you belong to with owner, member count and visibility. Access: read. REST: `GET /api/v1/otter/channels`. MCP: `otter_read → list_channels`.

No parameters.

Lists the Channels you belong to, in alphabetical order by name. Visibility is private or workspace. Use the channel_id with list_conversations to read one Channel or with share_conversation to share with all of its members.

Example response:

```json
{
  "channels": [
    {
      "channel_id": "ch_55",
      "name": "Customer Success",
      "members": 12,
      "owner": "you@example.com",
      "visibility": "private"
    }
  ]
}
```

### export_conversation

Export a conversation as TXT, DOCX, PDF or SRT, or its audio as MP3, and return a download link. Access: read. REST: `GET /api/v1/otter/conversations/{conversation_id}/export`. MCP: `otter_read → export_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |
| `format` | enum | yes | txt, docx, pdf, srt or mp3 (audio). |
| `show_speaker_names` | boolean | no | Text formats only. Default: true. |
| `show_timestamps` | boolean | no | Text formats only. Default: false. |
| `show_highlights` | boolean | no | Text formats only. Default: false. |

Runs Otter's Export for one conversation and returns a download link and the file name. Text formats can include speaker names, timestamps and highlights. mp3 exports the audio. Basic plan accounts can export TXT only; the call fails with that reason on other formats. Exports reach only you, so they run without asking.

Example response:

```json
{
  "conversation_id": "cv_7f3a91",
  "format": "docx",
  "file_name": "Pricing review with Acme.docx",
  "download_url": "https://files.cotlet.dev/exports/example-pricing-review.docx"
}
```

### bulk_export_conversations

Export many conversations as one ZIP. Otter emails you the download link. Business and Enterprise plans. Access: read. REST: `GET /api/v1/otter/export-conversations/bulk`. MCP: `otter_read → bulk_export_conversations`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_ids` | string[] | yes | Conversation IDs from list_conversations. |
| `formats` | string[] | yes | One or more of txt, docx, pdf, srt. |

Starts Otter's bulk export for the conversations you list, in one or more formats. Otter builds the ZIP and emails the download link to your account address when it is ready, so the call returns a started status, not the file. Bulk export is available on the Business and Enterprise plans; other plans get a plan error. The mail goes to you only, so it runs without asking.

Example response:

```json
{
  "export_id": "ex_9d20",
  "status": "started",
  "conversations": 3,
  "formats": [
    "docx"
  ],
  "delivery": "Otter emails the ZIP link to your account address"
}
```

### share_conversation

Share a conversation with people by email or with a Channel, as Viewer or Collaborator. Access: write, asks the user first. REST: `POST /api/v1/otter/conversations/{conversation_id}/share`. MCP: `otter_write → share_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |
| `emails` | string[] | no | Email addresses to share with. Give emails, a channel_id or both. |
| `channel_id` | string | no | Channel ID from list_channels. |
| `permission` | enum | no | viewer or collaborator. Default: viewer. |

Adds people or a Channel to a conversation's sharing list with the permission you choose. A Viewer can view and play back; a Collaborator can edit, export and add Takeaways. People who already have access are returned as already_shared and are not changed. If your workspace admin turned on Invite teammates to Workspace as free trial members, an address on the workspace domain also gets a workspace invite. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "cv_7f3a91",
  "shared_with": [
    {
      "email": "dana@example.com",
      "permission": "viewer"
    },
    {
      "email": "lee@example.com",
      "permission": "viewer"
    }
  ],
  "already_shared": []
}
```

### unshare_conversation

Remove a person or a Channel from the sharing list of a conversation. Access: write, asks the user first. REST: `POST /api/v1/otter/conversations/{conversation_id}/unshare`. MCP: `otter_write → unshare_conversation`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |
| `email` | string | no | Person to remove. Give an email or a channel_id. |
| `channel_id` | string | no | Channel to remove. |

Removes one person or one Channel from a conversation's sharing list, the same as Remove in the Share dialog. They lose access at once. You can share again at any time with share_conversation. Public link settings are not changed. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "cv_7f3a91",
  "removed": "lee@example.com",
  "shared_with": [
    {
      "email": "dana@example.com",
      "permission": "viewer"
    }
  ]
}
```

### add_highlight

Highlight a passage of a transcript, or remove an existing highlight. Access: write. REST: `POST /api/v1/otter/conversations/{conversation_id}/highlights`. MCP: `otter_write → add_highlight`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `conversation_id` | string | yes | Conversation ID from list_conversations or search_transcripts. |
| `text` | string | yes | The passage exactly as it appears in the transcript. |
| `remove` | boolean | no | true removes the highlight. Default: false. |

Finds the passage in the transcript and highlights it. If the text is not found or appears more than once, the call fails and lists the matches, so nothing is highlighted by guess. Set remove to true to remove the highlight again. People the conversation is shared with, and anyone with a public link, can see highlights, so keep notes for yourself out of them. add_highlight runs without asking first: it sends nothing to anyone and is undone with one call.

Example response:

```json
{
  "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
}
```

### complete_action_item

Check an action item off, or reopen it. Access: write. REST: `POST /api/v1/otter/action-items/{action_item_id}/complete`. MCP: `otter_write → complete_action_item`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `action_item_id` | string | yes | Action item ID from list_action_items. |
| `completed` | boolean | no | false reopens the item. Default: true. |

Checks an action item off, which moves it to Completed, or reopens it when completed is false. The change shows in the conversation the item came from. complete_action_item runs without asking first: it sends nothing to anyone and is undone with one call.

Example response:

```json
{
  "action_item_id": "ai_204",
  "text": "Send revised quote by Wednesday",
  "completed": true
}
```

### assign_action_item

Reassign an action item to another user. Access: write, asks the user first. REST: `POST /api/v1/otter/action-items/{action_item_id}/assign`. MCP: `otter_write → assign_action_item`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `action_item_id` | string | yes | Action item ID from list_action_items. |
| `assignee_email` | string | yes | Email of the new assignee. |

Hands an action item to another user. It leaves your Action Items list at once and appears in theirs. You get it back only if they reassign it or you assign it again inside the conversation. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "action_item_id": "ai_204",
  "text": "Send revised quote by Wednesday",
  "assignee": "dana@example.com"
}
```

### import_audio

Import an audio or video file from a URL for transcription, summary and action items. Access: write, asks the user first. REST: `POST /api/v1/otter/audios`. MCP: `otter_write → import_audio`.

| Parameter | Type | Required | Description |
|---|---|---|---|
| `file_url` | string | yes | HTTPS URL of the audio or video file, reachable without a login. |
| `name` | string | no | Name for the conversation. Default: the file name. |

Fetches the file from the URL and imports it into your Otter account as a new conversation. The file must be up to 5 GB, in a supported audio or video format, and reachable without a login. The import counts toward your plan's transcription limits and the transcript is ready when get_conversation shows the processing as finished. By default you confirm each call; you can switch that off for this tool.

Example response:

```json
{
  "conversation_id": "cv_a7710e",
  "name": "Discovery call 14 Oct",
  "status": "processing"
}
```

## How do I connect Otter.ai to Claude Code, Codex or Cursor?

Connecting Otter.ai takes three steps: sign up, sign in to Otter.ai once in your Cloud Browser and enable it for agents, then add one MCP server or call the REST API with the same key.

### Connect Otter.ai to your agent.

1. **Create an account** Sign up and add Otter.ai in the console. Your API key is there too.

2. **Sign in to Otter.ai in your Cloud Browser** Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Otter.ai there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.

3. **Add Cotlet to your agent** Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.

   Claude Code:

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

   Cursor:

```
{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}
```

   Codex:

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

4. **Ask your agent** Ask in plain words. Your agent finds the Otter.ai tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.

```
After each customer call today, share the Otter conversation with the attendees as viewers and tell me who got access. Skip anyone who already has it.
```

### Call Otter.ai from your scripts.

1. **Export your API key** Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.

```
export COTLET_API_KEY="cotlet_..."
```

2. **Call a tool** Every tool is an endpoint under /api/v1/otter with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.

```
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."}'
```

3. **Read the result** You get plain JSON back, ready for your script. A failed call costs nothing.

```
{
  "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
}
```

## Why use Cotlet for Otter.ai?

**Built for agents**

- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with Claude Code, Codex and Cursor.

**Your login stays yours**

- You sign in to Otter.ai yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no CAPTCHA solving, no MFA bypass.

**You stay in control**

- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.

**Kept working for you**

- We test every integration every 6 hours.
- When Otter.ai changes, the tool pauses until we fix it.
- Failed calls cost nothing.

## Is it safe to connect Otter.ai to Cotlet?

Yes. You sign in to Otter.ai yourself, in your own Cloud Browser, and we never save your password. Your agents only get Otter.ai once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.

- **A+ on Qualys SSL Labs**: Encryption in transit: TLS setup and certificates, on all four server addresses. [Live result](https://www.ssllabs.com/ssltest/analyze.html?d=cotlet.dev)
- **A+ on securityheaders.com**: Browser protections sent with every page, all six headers present. [Live result](https://securityheaders.com/?q=cotlet.dev&followRedirects=on)
- **A+ on Mozilla Observatory**: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. [Live result](https://developer.mozilla.org/en-US/observatory/analyze?host=cotlet.dev)
- **Clean on Sucuri SiteCheck**: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. [Live result](https://sitecheck.sucuri.net/results/cotlet.dev)

[How Cotlet protects your access](https://cotlet.dev/security.md)

### Common concerns

**Who runs Cotlet?**

Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.

**Is this an official Otter.ai integration?**

No, Cotlet is independent of Otter.ai. Otter.ai's own API is open only to approved partners. Cotlet works through your own Otter.ai account, the way you use Otter.ai in the browser, so you need no partner approval and no developer setup.

**What about client data and GDPR?**

Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.

**Can I start with read only?**

Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.

**Is it reliable?**

Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.

**How do I stop?**

Press Disable for agents next to Otter.ai in your console: your agents lose access at once and you stay signed in. Signing out of Otter.ai in the browser works too, and Reset browser deletes the whole profile.

## Is there a Otter.ai MCP server on GitHub?

Yes. Community Otter MCP servers and command-line tools exist on GitHub, usually maintained by one person. You install one on your own computer, sign it in to Otter, and keep it running yourself; when Otter changes its site, it stops working until you or the maintainer fix it. Cotlet hosts the same kind of server for you, and our team keeps it working. Otter's official MCP server is a fair choice if you only need to search and read.

|  | GitHub MCP server | Cotlet |
|---|---|---|
| Setup | Clone the repo, install it, sign it in to Otter, add it to each MCP client | Sign up, sign in to Otter once, add one MCP server or API key |
| When Otter changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your Otter session | In a file on your computer, readable by any program you run | In your own Cloud Browser in the EU, profile encrypted, only for the apps you enable, disabled for agents in one click |
| When the session expires | Tools fail until you sign in again by hand | Your Cloud Browser keeps you signed in; if Otter logs you out, your agent gets a link to sign in again |
| Upkeep | You update, monitor and debug it yourself | Nothing to host or update |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |

### Which one fits you

**Pick Cotlet if**

- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Otter.ai changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off

**Pick an open-source server if**

- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client

## How much does the Otter.ai API cost?

Free 7-day trial with 2,000 credits, no card needed. After that, the Otter.ai API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 20 to 30 credits (25 for most tools, about $0.10 to $0.15), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.

| Credits | Price, one time | Calls at 25 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 200 | $5.80 |
| 15,000 | $79 | 600 | $5.27 |
| 32,000 | $149 | 1,280 | $4.66 |
| 60,000 | $249 | 2,400 | $4.15 |

Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the `Authorization: Bearer` header. [See full pricing](https://cotlet.dev/pricing.md)

## How Cotlet holds your access

Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Otter.ai account.

- **Company details:** Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. [Terms of service](https://cotlet.dev/terms)
- **Your sign-in:** You sign in to Otter.ai yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Otter.ai only after you enable it. When Otter.ai signs you out, your agent gives you a link to sign in again. [Security](https://cotlet.dev/security.md)
- **Revoking access:** Press Disable for agents next to Otter.ai, sign out of Otter.ai in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- **What we never do:** Store passwords, solve CAPTCHAs or bypass MFA.
- **Otter.ai's terms:** You use your own Otter.ai account and stay responsible for following Otter.ai's terms. Cotlet is independent and not affiliated with Otter.ai. [Terms](https://cotlet.dev/terms)
- **Contact:** Questions about the company, security or an app: [contact@cotlet.dev](mailto:contact@cotlet.dev)

## Frequently asked questions

**How do I get access?**

Sign up free, open Otter.ai in the console and press Request access. Then you create your API key and connect Otter.ai there.

**Do I need to be technical?**

No. You sign in to Otter.ai once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.

**Is it safe to connect Otter.ai to Cotlet?**

Yes. You sign in to Otter.ai yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Otter.ai once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

**Is a hosted server safer than a local one? My Otter.ai sign-in would leave my computer.**

On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Otter.ai cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.

**Why does Cotlet send requests instead of clicking in my browser?**

To be fast, Cotlet doesn't click through Otter.ai's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Otter.ai sees the same browser and IP you signed in with, and every request is listed in your Background activity.

**What if someone gets my Cotlet API key?**

The key holds no Otter.ai login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.

**Why a signed-in browser and not OAuth, like other integration platforms?**

Otter.ai offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).

**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 post or send messages in Otter.ai without asking me?**

No. Every call to share_conversation, unshare_conversation, assign_action_item or import_audio waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. add_highlight, complete_action_item runs without asking, because it sends nothing to anyone and one call undoes it.

**Can I use the Otter.ai API in n8n?**

Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/otter from the HTTP Request node.

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

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.

## For AI agents: sign your user up

Is your user asking you to sign them up for Cotlet? You can do it for them, no account or key needed.

1. Read the fields and their allowed values: GET https://cotlet.dev/api/v1/access-requests
2. Ask the user for each value: email, apps, what you will do with them. If they leave the password to you, generate a strong one and show it to them.
3. Show the user what you will send, then POST it as JSON to https://cotlet.dev/api/v1/access-requests.

One call creates the account and sends the access request; we email the user when access is granted.