MailboxValidator for AI agents
MailboxValidator is an email verification API that checks syntax, mail server availability, and whether an address is free or disposable. 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 MailboxValidator.
Validate an email address
Check an address's syntax and mail server status before it is added to a contact list.
Flag disposable signup addresses
Check whether a signup email comes from a disposable provider so it can be routed for review.
Check for free email providers
Check whether a submitted work email is actually a free consumer address, read-only.
3 MailboxValidator actions, graded by risk.
Every MailboxValidator 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.
- mailboxvalidator.validate_emailValidate Email
- mailboxvalidator.check_free_emailCheck Free Email
- mailboxvalidator.check_disposable_emailCheck Disposable Email
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
MailboxValidator in three steps.
- 01Your users connect MailboxValidatorThey add their MailboxValidator api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls MailboxValidator through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mailboxvalidator', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How MailboxValidator connects.
Users add their MailboxValidator 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 MailboxValidator 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 MailboxValidator from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
MailboxValidator and Arc0, answered.
Can I use MailboxValidator with Claude, ChatGPT or Cursor?
Yes. Connect MailboxValidator 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 MailboxValidator actions you allow.
How do users connect MailboxValidator?
Users add their MailboxValidator 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 MailboxValidator actions can my agent take?
3 in total: 3 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in MailboxValidator?
Yes. Allow read actions and deny writes in the MailboxValidator policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call MailboxValidator too?
Yes. The same MailboxValidator connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug MailboxValidator into your agent.
Your users connect MailboxValidator once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan