Avoma for AI agents
Avoma records, transcribes, and analyzes sales and customer calls, giving revenue teams meeting notes, scorecards, and conversation insights without anyone taking manual notes. 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 Avoma.
Pull a call's summary and notes
Retrieve the recording, transcript, and notes for a specific sales call before writing a CRM update.
Check a rep's scorecard
List scorecard evaluations for a call to see how a rep performed against the team's talk-track before coaching them.
Find calls missing a follow-up
List calls from the past week as a read-only check to find ones missing a follow-up summary.
16 Avoma actions, graded by risk.
Every Avoma action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
15Look things up. Allowed by default.
- avoma.get_callGet Call
- avoma.list_callsList Calls
- avoma.list_notesList Notes
- avoma.list_usersList Users
- avoma.get_meetingGet Meeting
- avoma.get_recordingGet Recording
- avoma.list_meetingsList Meetings
- avoma.list_snippetsList Snippets
- avoma.list_webhooksList Webhooks
- avoma.list_transcriptionsList Transcriptions
- avoma.get_meeting_analysisGet Meeting Analysis
- avoma.get_engagement_summaryGet Engagement Summary
- avoma.list_engagement_metricsList Engagement Metrics
- avoma.list_scorecard_evaluationsList Scorecard Evaluations
- avoma.list_configuration_resourcesList Configuration Resources
write
1Create and change things. Allow, or ask the user first.
- avoma.create_callCreate Call
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Avoma in three steps.
- 01Your users connect AvomaThey add their Avoma api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Call” can wait for the user to approve.
- 03Any agent can actYour agent calls Avoma through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('avoma', { read: 'allow', write: 'ask', // create_call destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Avoma connects.
Users add their Avoma api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Avoma 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
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Avoma from any agent.
Avoma and Arc0, answered.
Can I use Avoma with Claude, ChatGPT or Cursor?
Yes. Connect Avoma 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 Avoma actions you allow.
How do users connect Avoma?
Users add their Avoma api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Avoma actions can my agent take?
16 in total: 15 read, 1 write and 0 destructive, such as “create Call”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Avoma?
Yes. Allow read actions and deny writes in the Avoma policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Avoma too?
Yes. The same Avoma connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Avoma into your agent.
Your users connect Avoma once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan