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.

EmailAPI keyMCP + RESTmailslurp.com
AUDIT LOG · MAILSLURPPOLICY: acme-support
09:41:07 · claude · u_8f2read
mailslurp.list_emails
List Emails✓ allowed · 212ms
09:41:08 · claude · u_8f2read
mailslurp.get_email
Get Email✓ allowed · 164ms
09:41:09 · claude · u_8f2write
mailslurp.create_inbox
Create Inbox✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
mailslurp.delete_inbox
Delete Inbox✕ blocked · policy: deny
EVERY MAILSLURP CALL, ON THE RECORD
01 · USE CASES

What agents do in MailSlurp.

01

Create a test inbox

Create a disposable inbox to test an application's outgoing email flow without touching a real mailbox.

02

Check a received email

Read a specific email received in a test inbox to verify its content, read-only.

03

Approve before deleting an inbox

Require approval before deleting an inbox, since any emails stored in it would be lost.

02 · ACTIONS

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

10

Look things up. Allowed by default.

  • mailslurp.get_email
    Get Email
  • mailslurp.get_inbox
    Get Inbox
  • mailslurp.list_emails
    List Emails
  • mailslurp.list_domains
    List Domains
  • mailslurp.list_inboxes
    List Inboxes
  • mailslurp.list_contacts
    List Contacts
  • mailslurp.list_templates
    List Email Templates
  • mailslurp.get_account_info
    Get Account Info
  • mailslurp.list_sent_emails
    List Sent Emails
  • mailslurp.list_contact_groups
    List Contact Groups

write

3

Create and change things. Allow, or ask the user first.

  • mailslurp.send_email
    Send Email
  • mailslurp.create_inbox
    Create Inbox
  • mailslurp.update_inbox
    Update Inbox

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • mailslurp.delete_inbox
    Delete Inbox
03 · HOW IT WORKS

MailSlurp in three steps.

  1. 01Your users connect MailSlurpThey add their MailSlurp api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Inbox” can wait for the user, and “delete Inbox” can be denied outright.
  3. 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.
POLICY.TS
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
04 · AUTH AND DATA

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
05 · WORKS WITH

Use MailSlurp from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

MailSlurp and Arc0, answered.

Q01

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.

Q02

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.

Q03

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.

Q04

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.

Q05

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.

Get started

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