Addresszen for AI agents
AddressZen provides address autocomplete and verification so forms only accept real, deliverable addresses. Developers use it in checkout and signup flows for US addresses. 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 Addresszen.
Resolve a US address
Turn a partial or messy US address into a standardized, verified address for a shipping or billing record.
Check API key availability
Confirm an API key is active and has capacity before running a batch of address lookups.
Standardize an address for a form
Clean up a customer-entered US address so it matches postal formatting before it is saved.
2 Addresszen actions, graded by risk.
Every Addresszen 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.
- addresszen.resolve_address_usaResolve Address USA
write
1Create and change things. Allow, or ask the user first.
- addresszen.key_availabilityKey Availability
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Addresszen in three steps.
- 01Your users connect AddresszenThey add their Addresszen api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “key Availability” can wait for the user to approve.
- 03Any agent can actYour agent calls Addresszen through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('addresszen', { read: 'allow', write: 'ask', // key_availability destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Addresszen connects.
Users add their Addresszen 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 Addresszen 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 Addresszen from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Addresszen and Arc0, answered.
Can I use Addresszen with Claude, ChatGPT or Cursor?
Yes. Connect Addresszen 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 Addresszen actions you allow.
How do users connect Addresszen?
Users add their Addresszen 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 Addresszen actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “key Availability”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Addresszen?
Yes. Allow read actions and deny writes in the Addresszen policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Addresszen too?
Yes. The same Addresszen connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Addresszen into your agent.
Your users connect Addresszen once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan