Vestaboard for AI agents
Vestaboard is a mechanical split-flap display that shows messages, used by offices and homes that want a physical, glanceable message board. 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 Vestaboard.
Send a message to the board
Post a new message to display on a connected Vestaboard.
List active subscriptions
Check which boards are subscribed and available to send to, a read-only check.
Confirm the message before sending
Review the exact text and layout before it's pushed to the physical board.
2 Vestaboard actions, graded by risk.
Every Vestaboard 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.
- vestaboard.list_subscriptionsList Subscriptions
write
1Create and change things. Allow, or ask the user first.
- vestaboard.subscription_api_send_messageSend Message to Vestaboard
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Vestaboard in three steps.
- 01Your users connect VestaboardThey add their Vestaboard api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “send Message to Vestaboard” can wait for the user to approve.
- 03Any agent can actYour agent calls Vestaboard through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('vestaboard', { read: 'allow', write: 'ask', // subscription_api_send_message destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Vestaboard connects.
Users add their Vestaboard 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 Vestaboard 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 Vestaboard from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Vestaboard and Arc0, answered.
Can I use Vestaboard with Claude, ChatGPT or Cursor?
Yes. Connect Vestaboard 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 Vestaboard actions you allow.
How do users connect Vestaboard?
Users add their Vestaboard 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 Vestaboard actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “send Message to Vestaboard”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Vestaboard?
Yes. Allow read actions and deny writes in the Vestaboard policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Vestaboard too?
Yes. The same Vestaboard connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Vestaboard into your agent.
Your users connect Vestaboard 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