Reteno for AI agents
Reteno is a customer engagement platform for running email, SMS, and push campaigns based on contact data and behavioral events. 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 Reteno.
Look up a contact
Get a contact's profile and segments before deciding which campaign to add them to.
Track a behavioral event
Track an event like a purchase or signup so a workflow can trigger the right follow-up message.
Check balance before a send
Get the account balance to confirm there's enough credit before a large campaign goes out.
14 Reteno actions, graded by risk.
Every Reteno action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
12Look things up. Allowed by default.
- reteno.get_contactGet Contact
- reteno.list_contactsList Contacts
- reteno.list_segmentsList Segments
- reteno.list_workflowsList Workflows
- reteno.get_account_infoGet Account Info
- reteno.list_address_booksList Address Books
- reteno.get_account_balanceGet Account Balance
- reteno.list_contact_fieldsList Contact Fields
- reteno.list_contact_messagesList Contact Messages
- reteno.get_contact_import_statusGet Contact Import Status
- reteno.list_subscription_categoriesList Subscription Categories
- reteno.track_eventTrack Event
write
2Create and change things. Allow, or ask the user first.
- reteno.upsert_contactUpsert Contact
- reteno.upsert_contactsUpsert Contacts
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Reteno in three steps.
- 01Your users connect RetenoThey add their Reteno api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “upsert Contact” can wait for the user to approve.
- 03Any agent can actYour agent calls Reteno through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('reteno', { read: 'allow', write: 'ask', // upsert_contact destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Reteno connects.
Users add their Reteno 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 Reteno 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 Reteno from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Reteno and Arc0, answered.
Can I use Reteno with Claude, ChatGPT or Cursor?
Yes. Connect Reteno 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 Reteno actions you allow.
How do users connect Reteno?
Users add their Reteno 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 Reteno actions can my agent take?
14 in total: 12 read, 2 write and 0 destructive, such as “upsert Contact”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Reteno?
Yes. Allow read actions and deny writes in the Reteno policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Reteno too?
Yes. The same Reteno connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Reteno into your agent.
Your users connect Reteno once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan