Seven.io for AI agents
Seven.io provides APIs for sending SMS and voice messages, managing contacts, and tracking delivery and spend. Businesses use it to reach customers directly on their phones. 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 Seven.io.
Send an SMS to a customer
Send a text message, like an appointment reminder or order update, to a customer's phone number.
Check balance before a bulk send
Look up the account balance and per-message pricing before sending a large batch of SMS messages.
Track a message's delivery
Query the message journal to confirm whether a sent SMS was delivered.
11 Seven.io actions, graded by risk.
Every Seven.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- seven_io.get_balanceGet Balance
- seven_io.list_groupsList Contact Groups
- seven_io.get_analyticsGet Analytics
- seven_io.list_contactsList Contacts
- seven_io.get_sms_pricingGet SMS Pricing
- seven_io.query_message_journalQuery Message Journal
write
4Create and change things. Allow, or ask the user first.
- seven_io.send_smsSend SMS
- seven_io.create_contactCreate Contact
- seven_io.update_contactUpdate Contact
- seven_io.format_phone_numbersFormat Phone Numbers
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- seven_io.delete_contactDelete Contact
Seven.io in three steps.
- 01Your users connect Seven.ioThey add their Seven.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Contact” can wait for the user, and “delete Contact” can be denied outright.
- 03Any agent can actYour agent calls Seven.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('seven_io', { read: 'allow', write: 'ask', // create_contact destructive: 'deny', // delete_contact }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Seven.io connects.
Users add their Seven.io 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 Seven.io 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 Seven.io from any agent.
Seven.io and Arc0, answered.
Can I use Seven.io with Claude, ChatGPT or Cursor?
Yes. Connect Seven.io 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 Seven.io actions you allow.
How do users connect Seven.io?
Users add their Seven.io 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 Seven.io actions can my agent take?
11 in total: 6 read, 4 write and 1 destructive, such as “create Contact”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Seven.io?
Yes. Actions like “delete Contact” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Seven.io too?
Yes. The same Seven.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Seven.io into your agent.
Your users connect Seven.io 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