MailSlurp for AI agents
MailSlurp provides programmable email inboxes for developers to send, receive, and test email flows through an API, without needing a real mailbox. 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 MailSlurp.
Create a test inbox
Create a disposable inbox to test an application's outgoing email flow without touching a real mailbox.
Check a received email
Read a specific email received in a test inbox to verify its content, read-only.
Approve before deleting an inbox
Require approval before deleting an inbox, since any emails stored in it would be lost.
14 MailSlurp actions, graded by risk.
Every MailSlurp action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
10Look things up. Allowed by default.
- mailslurp.get_emailGet Email
- mailslurp.get_inboxGet Inbox
- mailslurp.list_emailsList Emails
- mailslurp.list_domainsList Domains
- mailslurp.list_inboxesList Inboxes
- mailslurp.list_contactsList Contacts
- mailslurp.list_templatesList Email Templates
- mailslurp.get_account_infoGet Account Info
- mailslurp.list_sent_emailsList Sent Emails
- mailslurp.list_contact_groupsList Contact Groups
write
3Create and change things. Allow, or ask the user first.
- mailslurp.send_emailSend Email
- mailslurp.create_inboxCreate Inbox
- mailslurp.update_inboxUpdate Inbox
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- mailslurp.delete_inboxDelete Inbox
MailSlurp in three steps.
- 01Your users connect MailSlurpThey add their MailSlurp api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Inbox” can wait for the user, and “delete Inbox” can be denied outright.
- 03Any agent can actYour agent calls MailSlurp through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mailslurp', { read: 'allow', write: 'ask', // create_inbox destructive: 'deny', // delete_inbox }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How MailSlurp connects.
Users add their MailSlurp 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 MailSlurp 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 MailSlurp from any agent.
MailSlurp and Arc0, answered.
Can I use MailSlurp with Claude, ChatGPT or Cursor?
Yes. Connect MailSlurp 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 MailSlurp actions you allow.
How do users connect MailSlurp?
Users add their MailSlurp 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 MailSlurp actions can my agent take?
14 in total: 10 read, 3 write and 1 destructive, such as “create Inbox”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in MailSlurp?
Yes. Actions like “delete Inbox” 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 MailSlurp too?
Yes. The same MailSlurp connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug MailSlurp into your agent.
Your users connect MailSlurp once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan