Circleback for AI agents
Circleback connects to meeting recordings and transcripts, letting an agent search past meetings, action items, and related emails and contacts. 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.
What agents do in Circleback.
Search past meeting transcripts
Search across past meeting transcripts for a topic instead of re-listening to recordings.
Pull action items from a meeting
Pull the action items captured in a specific meeting to follow up on owners.
Look up a company mentioned
Look up a company that came up in a meeting before an agent references it again.
11 Circleback actions, graded by risk.
Every Circleback action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
11Look things up. Allowed by default.
- circleback.list_tagsListtags
- circleback.find_profilesFindprofiles
- circleback.search_emailsSearchemails
- circleback.find_companiesFindcompanies
- circleback.search_meetingsSearchmeetings
- circleback.search_transcriptsSearchtranscripts
- circleback.search_action_itemsSearchactionitems
- circleback.search_calendar_eventsSearchcalendarevents
- circleback.search_support_articlesSearchsupportarticles
- circleback.get_transcripts_for_meetingsGettranscriptsformeetings
- circleback.read_meetingsReadmeetings
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Circleback in three steps.
- 01Your users connect CirclebackThey sign in to Circleback on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Circleback through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('circleback', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Circleback connects.
Circleback runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Circleback through the same endpoint, policies and audit log as every other app.
The same Circleback 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
Use Circleback from any agent.
Circleback and Arc0, answered.
Can I use Circleback with Claude, ChatGPT or Cursor?
Yes. Connect Circleback 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 Circleback actions you allow.
How do users connect Circleback?
Circleback runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Circleback through the same endpoint, policies and audit log as every other app.
Which Circleback actions can my agent take?
11 in total: 11 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Circleback?
Yes. Allow read actions and deny writes in the Circleback policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Circleback too?
Yes. The same Circleback connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Circleback into your agent.
Your users connect Circleback once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan