Otter.ai for AI agents

Otter.ai records and transcribes meetings, letting users search past conversations and pull full transcripts. Teams use it to capture meeting notes without manual note-taking. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

MeetingsOAuth 2.0 (MCP)MCP + RESTotter.ai
AUDIT LOG · OTTER.AIPOLICY: acme-support
09:41:09 · claude · u_8f2write
otter_ai.otter_fetch
Otter fetch✓ approved · approved by user
EVERY OTTER.AI CALL, ON THE RECORD
01 · USE CASES

What agents do in Otter.ai.

01

Search past meetings for a topic

Search authorized meetings and conversations for mentions of a project or decision.

02

Fetch a meeting transcript

Retrieve the full transcript of a recorded meeting for summarizing or sharing.

03

Check user profile read-only

Look up the authenticated user's profile before running a search on their behalf.

02 · ACTIONS

3 Otter.ai actions, graded by risk.

Every Otter.ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

0

Look things up. Allowed by default.

  • No read actions.

write

3

Create and change things. Allow, or ask the user first.

  • otter_ai.otter_fetch
    Otter fetch
  • otter_ai.otter_search
    Otter search
  • otter_ai.otter_get_user_info
    Otter get user info

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Otter.ai in three steps.

  1. 01Your users connect Otter.aiThey sign in to Otter.ai on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, and writes like “otter fetch” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Otter.ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('otter_ai', {
  read: 'allow',
  write: 'ask',        // otter_fetch
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Otter.ai connects.

Otter.ai runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Otter.ai through the same endpoint, policies and audit log as every other app.

The same Otter.ai connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
OAuth 2.0 (MCP)
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Otter.ai from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Otter.ai and Arc0, answered.

Q01

Can I use Otter.ai with Claude, ChatGPT or Cursor?

Yes. Connect Otter.ai to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Otter.ai actions you allow.

Q02

How do users connect Otter.ai?

Otter.ai runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Otter.ai through the same endpoint, policies and audit log as every other app.

Q03

Which Otter.ai actions can my agent take?

3 in total: 0 read, 3 write and 0 destructive, such as “otter fetch”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Otter.ai?

Yes. Allow read actions and deny writes in the Otter.ai policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Otter.ai too?

Yes. The same Otter.ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Otter.ai into your agent.

Your users connect Otter.ai once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan