Postgrid for AI agents
PostGrid automates direct mail and address verification, letting businesses send letters, postcards, and checks programmatically. Operations teams use it to trigger physical mail from software. 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.
Send a letter to a contact
Create and send a letter to a physical address as part of an automated workflow.
Check a letter's tracking status read-only
Look up a tracker to see whether a mailed letter has been delivered.
Cancel a cheque with approval
Cancel a mailed cheque only after finance confirms the payment should not go out.
60 Postgrid actions, graded by risk.
Every Postgrid action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
29Look things up. Allowed by default.
- postgrid.get_boxGet Box
- postgrid.get_chequeGet Cheque
- postgrid.get_letterGet Letter
- postgrid.list_boxesList Box Orders
- postgrid.get_contactGet Contact
- postgrid.get_trackerGet Tracker
- postgrid.get_webhookGet Webhook
- postgrid.list_eventsList Webhook Events
- postgrid.get_postcardGet Postcard
- postgrid.get_templateGet Template
- postgrid.list_chequesList Cheques
- postgrid.list_lettersList Letters
- postgrid.list_contactsList Contacts
- postgrid.list_trackersList Trackers
- postgrid.list_webhooksList Webhooks
- postgrid.list_postcardsList Postcards
write
19Create and change things. Allow, or ask the user first.
- postgrid.create_boxCreate Box
- postgrid.create_chequeCreate Cheque
- postgrid.create_letterCreate Letter
- postgrid.create_contactCreate Contact
- postgrid.create_trackerCreate Tracker
- postgrid.create_webhookCreate Webhook
- postgrid.update_trackerUpdate Tracker
- postgrid.update_webhookUpdate Webhook
- postgrid.create_postcardCreate Postcard
- postgrid.create_templateCreate Template
- postgrid.update_templateUpdate Template
- postgrid.create_bank_accountCREATE_BANK_ACCOUNT
- postgrid.create_return_envelopeCreate Return Envelope
- postgrid.create_return_envelope_orderCreate Return Envelope Order
- postgrid.create_template_editor_sessionCreate Template Editor Session
- postgrid.progress_test_boxProgress Test Box
destructive
12Delete, cancel or archive. Ask first, or deny outright.
- postgrid.cancel_boxCancel Box
- postgrid.cancel_chequeCancel Cheque
- postgrid.delete_contactDelete Contact
- postgrid.delete_trackerDelete Tracker
- postgrid.delete_webhookDelete Webhook
- postgrid.cancel_postcardCancel Postcard
- postgrid.delete_templateDelete Template
- postgrid.delete_bank_accountDelete Bank Account
- postgrid.cancel_cheque_with_noteCancel Cheque with Note
- postgrid.cancel_postcard_with_noteCancel Postcard With Note
- postgrid.cancel_return_envelope_orderCancel Return Envelope Order
- postgrid.delete_template_editor_sessionDelete Template Editor Session
Postgrid in three steps.
- 01Your users connect PostgridThey add their Postgrid api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Box” can wait for the user, and “delete Contact” can be denied outright.
- 03Any agent can actYour agent calls Postgrid 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', { read: 'allow', write: 'ask', // create_box 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 Postgrid connects.
Users add their Postgrid 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 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 from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Postgrid and Arc0, answered.
Can I use Postgrid with Claude, ChatGPT or Cursor?
Yes. Connect Postgrid 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 actions you allow.
How do users connect Postgrid?
Users add their Postgrid 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 actions can my agent take?
60 in total: 29 read, 19 write and 12 destructive, such as “create Box”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Postgrid?
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 Postgrid too?
Yes. The same Postgrid connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Postgrid into your agent.
Your users connect Postgrid once, under your brand. Your agent gets 60 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan