Wati for AI agents
Wati runs WhatsApp Business messaging for marketing, sales, and support, used by businesses that handle customer conversations over WhatsApp at scale. 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 Wati.
Send a session message
Reply to a customer within an active WhatsApp conversation window.
Add a new contact
Add a customer's WhatsApp contact details to the account.
Confirm before updating chat status
Check with the user before marking a chat resolved, since it changes what the support team sees as open.
5 Wati actions, graded by risk.
Every Wati 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.
- wati.get_teamsGet Teams
write
4Create and change things. Allow, or ask the user first.
- wati.add_contactAdd Contact
- wati.update_chat_statusWati update chat status
- wati.send_session_messageSend Session Message
- wati.update_contact_attributesUpdate Contact Attributes
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Wati in three steps.
- 01Your users connect WatiThey add their Wati api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “send Session Message” can wait for the user to approve.
- 03Any agent can actYour agent calls Wati through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('wati', { read: 'allow', write: 'ask', // send_session_message destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Wati connects.
Users add their Wati 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 Wati 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 Wati from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Wati and Arc0, answered.
Can I use Wati with Claude, ChatGPT or Cursor?
Yes. Connect Wati 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 Wati actions you allow.
How do users connect Wati?
Users add their Wati 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 Wati actions can my agent take?
5 in total: 1 read, 4 write and 0 destructive, such as “send Session Message”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Wati?
Yes. Allow read actions and deny writes in the Wati policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Wati too?
Yes. The same Wati connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Wati into your agent.
Your users connect Wati once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan