Handwrite.io for AI agents
Handwrite.io creates and tracks physical handwritten card orders, choosing from real handwriting and stationery styles. Marketers fold it into their existing outreach and campaign workflow instead of running it separately. 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 Handwrite.io.
Send a handwritten card
Send a handwritten thank-you card to a client using a chosen handwriting and stationery style.
Check an order's status
Look up a placed card order to confirm it has shipped before following up with the recipient.
Browse stationery options
List available stationery styles to choose one that matches a brand's tone.
4 Handwrite.io actions, graded by risk.
Every Handwrite.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- handwrite_io.get_orderGet Order
- handwrite_io.list_stationeryList Stationery
- handwrite_io.list_handwriting_stylesList Handwriting Styles
write
1Create and change things. Allow, or ask the user first.
- handwrite_io.send_cardsSend Handwritten Cards
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Handwrite.io in three steps.
- 01Your users connect Handwrite.ioThey add their Handwrite.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “send Handwritten Cards” can wait for the user to approve.
- 03Any agent can actYour agent calls Handwrite.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('handwrite_io', { read: 'allow', write: 'ask', // send_cards destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Handwrite.io connects.
Users add their Handwrite.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 Handwrite.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 Handwrite.io from any agent.
Handwrite.io and Arc0, answered.
Can I use Handwrite.io with Claude, ChatGPT or Cursor?
Yes. Connect Handwrite.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 Handwrite.io actions you allow.
How do users connect Handwrite.io?
Users add their Handwrite.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 Handwrite.io actions can my agent take?
4 in total: 3 read, 1 write and 0 destructive, such as “send Handwritten Cards”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Handwrite.io?
Yes. Allow read actions and deny writes in the Handwrite.io policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Handwrite.io too?
Yes. The same Handwrite.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Handwrite.io into your agent.
Your users connect Handwrite.io once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan