Mocean for AI agents
Mocean provides SMS, voice, and WhatsApp messaging APIs for verification codes and customer engagement inside applications that need reliable delivery. 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 Mocean.
Send a WhatsApp message
Send a WhatsApp message to a customer's number for an order update.
Check an SMS message's status
Look up the delivery status of a sent SMS, a read-only check.
Approve before dialing a voice call
Require approval before placing an outbound voice call, since it reaches a real phone line.
6 Mocean actions, graded by risk.
Every Mocean action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- mocean.query_message_status_v2Query SMS Message Status V2
write
5Create and change things. Allow, or ask the user first.
- mocean.voice_dial_v2Voice Dial V2
- mocean.voice_hangup_v2Voice Hangup V2
- mocean.whats_app_send_message_v2WhatsApp Send Message V2
- mocean.voice_download_recording_v2Voice Download Recording V2
- mocean.whatsapp_incoming_webhook_v2WhatsApp Incoming Webhook V2
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Mocean in three steps.
- 01Your users connect MoceanThey add their Mocean api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “voice Dial V2” can wait for the user to approve.
- 03Any agent can actYour agent calls Mocean through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mocean', { read: 'allow', write: 'ask', // voice_dial_v2 destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mocean connects.
Users add their Mocean 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 Mocean 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 Mocean from any agent.
Mocean and Arc0, answered.
Can I use Mocean with Claude, ChatGPT or Cursor?
Yes. Connect Mocean 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 Mocean actions you allow.
How do users connect Mocean?
Users add their Mocean 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 Mocean actions can my agent take?
6 in total: 1 read, 5 write and 0 destructive, such as “voice Dial V2”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Mocean?
Yes. Allow read actions and deny writes in the Mocean policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Mocean too?
Yes. The same Mocean connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mocean into your agent.
Your users connect Mocean once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan