Thanks.io for AI agents
Thanks.io automates direct mail, including postcards, letters, and notecards with handwritten-style fonts, for businesses running physical mail campaigns alongside their digital marketing. 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 Thanks.io.
Preview a postcard before sending
Generate a preview of a postcard's design and message before it goes to print.
Add a recipient to a mailing list
Add a new address to a mailing list ahead of a scheduled send.
Confirm before sending a mail piece
Get sign-off before executing a stored send, since a printed and mailed postcard can't be recalled.
29 Thanks.io actions, graded by risk.
Every Thanks.io 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.
- thanks_io.list_mailing_listsList Mailing Lists
- thanks_io.list_image_templatesList Image Templates
- thanks_io.list_message_templatesList Message Templates
- thanks_io.list_handwriting_stylesList Handwriting Styles
write
21Create and change things. Allow, or ask the user first.
- thanks_io.send_postcardSend Postcard
- thanks_io.create_mailing_listCreate Mailing List
- thanks_io.add_recipient_to_mailing_listAdd Recipient to Mailing List
- thanks_io.orders_listList Orders
- thanks_io.recipients_updateUpdate Recipient
- thanks_io.sub_accounts_listList Sub Accounts
- thanks_io.sub_accounts_showGet Sub Account Details
- thanks_io.execute_stored_sendExecute Stored Send
- thanks_io.sub_accounts_createCreate Sub-Account
- thanks_io.sub_accounts_updateUpdate Sub-Account
- thanks_io.order_preview_letterPreview letter send
- thanks_io.stored_send_notecardStored Send Notecard
- thanks_io.stored_send_postcardStored Send Postcard
- thanks_io.order_preview_notecardPreview Notecard
- thanks_io.recipients_get_detailsGet Recipient Details
- thanks_io.recipients_create_multiCreate Multiple Recipients
destructive
4Delete, cancel or archive. Ask first, or deny outright.
- thanks_io.delete_sub_accountDelete Sub-Account
- thanks_io.delete_mailing_listDelete Mailing List
- thanks_io.delete_recipient_from_mailing_listDelete Recipient from Mailing List
- thanks_io.recipients_delete_by_addressDelete Recipient by Address
Thanks.io in three steps.
- 01Your users connect Thanks.ioThey add their Thanks.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Mailing List” can wait for the user, and “delete Sub-Account” can be denied outright.
- 03Any agent can actYour agent calls Thanks.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('thanks_io', { read: 'allow', write: 'ask', // create_mailing_list destructive: 'deny', // delete_sub_account }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Thanks.io connects.
Users add their Thanks.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 Thanks.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 Thanks.io from any agent.
Thanks.io and Arc0, answered.
Can I use Thanks.io with Claude, ChatGPT or Cursor?
Yes. Connect Thanks.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 Thanks.io actions you allow.
How do users connect Thanks.io?
Users add their Thanks.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 Thanks.io actions can my agent take?
29 in total: 4 read, 21 write and 4 destructive, such as “create Mailing List”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Thanks.io?
Yes. Actions like “delete Sub-Account” 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 Thanks.io too?
Yes. The same Thanks.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Thanks.io into your agent.
Your users connect Thanks.io once, under your brand. Your agent gets 29 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan