Callerapi for AI agents
CallerAPI provides branded caller ID lookups, helping a business show its name on outgoing calls and screen incoming numbers for spam or fraud risk. 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 Callerapi.
Look up an incoming number
Look up a phone number's details before deciding whether to trust or block an incoming call.
Check spam report subscriptions
List the webhook subscriptions for spam reports to confirm alerts are still wired up.
Subscribe to daily spam reports
Subscribe an account to daily spam reports so flagged numbers surface automatically.
7 Callerapi actions, graded by risk.
Every Callerapi action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- callerapi.get_user_informationGet User Information
- callerapi.list_webhook_subscriptionsList Webhook Subscriptions
- callerapi.get_phone_number_informationGet Phone Number Information
- callerapi.test_webhookTest Webhook
write
2Create and change things. Allow, or ask the user first.
- callerapi.subscribe_daily_reportsSubscribe to Daily Spam Reports
- callerapi.dispatch_reports_manuallyDispatch Reports Manually
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- callerapi.unsubscribe_daily_reportsUnsubscribe from Daily Reports
Callerapi in three steps.
- 01Your users connect CallerapiThey add their Callerapi api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “subscribe to Daily Spam Reports” can wait for the user, and “unsubscribe from Daily Reports” can be denied outright.
- 03Any agent can actYour agent calls Callerapi through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('callerapi', { read: 'allow', write: 'ask', // subscribe_daily_reports destructive: 'deny', // unsubscribe_daily_reports }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Callerapi connects.
Users add their Callerapi 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 Callerapi 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 Callerapi from any agent.
Callerapi and Arc0, answered.
Can I use Callerapi with Claude, ChatGPT or Cursor?
Yes. Connect Callerapi 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 Callerapi actions you allow.
How do users connect Callerapi?
Users add their Callerapi 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 Callerapi actions can my agent take?
7 in total: 4 read, 2 write and 1 destructive, such as “subscribe to Daily Spam Reports”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Callerapi?
Yes. Actions like “unsubscribe from Daily Reports” 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 Callerapi too?
Yes. The same Callerapi connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Callerapi into your agent.
Your users connect Callerapi once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan