PostGrid Verify for AI agents
PostGrid Verify autocompletes, verifies, and standardizes addresses in real time for individual or batch lookups. Developers use it to reduce failed deliveries from bad address data. 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 PostGrid Verify.
Verify a customer's address
Check an entered address against postal records before confirming a shipment.
Autocomplete an address field
Suggest address completions as a customer types during checkout.
Batch verify a mailing list
Validate a full list of addresses in one pass before a mail campaign goes out.
12 PostGrid Verify actions, graded by risk.
Every PostGrid Verify action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- postgrid_verify.get_lookup_infoGet Lookup Info
- postgrid_verify.get_autocomplete_previewsGet Autocomplete Previews
- postgrid_verify.get_intl_autocomplete_previewsGet International Autocomplete Previews
- postgrid_verify.parse_addressParse Address
- postgrid_verify.verify_addressVerify Address
- postgrid_verify.verify_batch_addressesBatch Verify Addresses with Mixed Format
- postgrid_verify.verify_intl_addresses_batchBatch Verify International Addresses
- postgrid_verify.verify_international_addressVerify International Address
- postgrid_verify.lookup_city_state_from_postalLookup City and State from Postal Code
write
3Create and change things. Allow, or ask the user first.
- postgrid_verify.suggest_addressesSuggest Addresses
- postgrid_verify.autocomplete_addressAutocomplete Address
- postgrid_verify.autocomplete_intl_addressAutocomplete International Address
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
PostGrid Verify in three steps.
- 01Your users connect PostGrid VerifyThey add their PostGrid Verify api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “suggest Addresses” can wait for the user to approve.
- 03Any agent can actYour agent calls PostGrid Verify through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('postgrid_verify', { read: 'allow', write: 'ask', // suggest_addresses destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How PostGrid Verify connects.
Users add their PostGrid Verify 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 PostGrid Verify 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 PostGrid Verify from any agent.
PostGrid Verify and Arc0, answered.
Can I use PostGrid Verify with Claude, ChatGPT or Cursor?
Yes. Connect PostGrid Verify 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 PostGrid Verify actions you allow.
How do users connect PostGrid Verify?
Users add their PostGrid Verify 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 PostGrid Verify actions can my agent take?
12 in total: 9 read, 3 write and 0 destructive, such as “suggest Addresses”. Your policies decide which of them each agent may call.
Can I make my agent read-only in PostGrid Verify?
Yes. Allow read actions and deny writes in the PostGrid Verify policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call PostGrid Verify too?
Yes. The same PostGrid Verify connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug PostGrid Verify into your agent.
Your users connect PostGrid Verify once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan