Get started

Mailtrap for AI agents

Mailtrap is an email delivery platform developers use to test transactional emails safely in a sandbox before sending them to real customers. 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.

Connect MailtrapSee the 49 actions ↓
Developer toolsBearer tokenMCP + RESTmailtrap.io
AUDIT LOG · MAILTRAPPOLICY: acme-support
09:41:07 · claude · u_8f2read
mailtrap.list_inboxes
List Inboxes✓ allowed · 212ms
09:41:08 · claude · u_8f2read
mailtrap.get_inbox
Get Inbox Attributes✓ allowed · 164ms
09:41:09 · claude · u_8f2write
mailtrap.create_contact
Create Contact✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
mailtrap.delete_contact
Delete Contact✕ blocked · policy: deny
EVERY MAILTRAP CALL, ON THE RECORD
01 · USE CASES

What agents do in Mailtrap.

01

Check sending stats by domain

Pull sending stats for a domain to check delivery health, a read-only lookup.

02

Create a contact list

Create a new contact list to organize recipients for a transactional campaign.

03

Approve before deleting a project

Require approval before deleting a project, since it removes its templates and sending history.

02 · ACTIONS

49 Mailtrap actions, graded by risk.

Every Mailtrap action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

26

Look things up. Allowed by default.

  • mailtrap.get_inbox
    Get Inbox Attributes
  • mailtrap.get_contact
    Get Contact
  • mailtrap.get_project
    Get Project by ID
  • mailtrap.list_inboxes
    List Inboxes
  • mailtrap.list_accounts
    List Accounts
  • mailtrap.list_messages
    List Messages in Inbox
  • mailtrap.list_projects
    List Projects
  • mailtrap.get_contact_list
    Get Contact List
  • mailtrap.get_message_html
    Get Message HTML Body
  • mailtrap.get_billing_usage
    Get Billing Usage
  • mailtrap.get_contact_field
    Get Contact Field
  • mailtrap.get_sending_stats
    Get Sending Stats
  • mailtrap.list_suppressions
    List Email Suppressions
  • mailtrap.get_contact_export
    Get Contact Export
  • mailtrap.get_contact_import
    Get Contact Import Status
  • mailtrap.get_email_template
    Get Email Template
+ 10 MORE

write

16

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

  • mailtrap.update_inbox
    Update inbox
  • mailtrap.create_contact
    Create Contact
  • mailtrap.update_contact
    Update contact
  • mailtrap.update_project
    Update project
  • mailtrap.create_contact_list
    Create Contact List
  • mailtrap.update_contact_list
    Update Contact List
  • mailtrap.create_contact_event
    Create Contact Event
  • mailtrap.create_contact_field
    Create Contact Field
  • mailtrap.update_contact_field
    Update Contact Field
  • mailtrap.create_contact_export
    Create Contact Export
  • mailtrap.create_email_template
    Create Email Template
  • mailtrap.create_sending_domain
    Create Sending Domain
  • mailtrap.update_email_template
    Update Email Template
  • mailtrap.clean_inbox
    Clean Inbox
  • mailtrap.import_contacts
    Import Contacts
  • mailtrap.mark_inbox_as_read
    Mark Inbox as Read

destructive

7

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

  • mailtrap.delete_contact
    Delete Contact
  • mailtrap.delete_project
    Delete Project
  • mailtrap.delete_contact_list
    Delete Contact List
  • mailtrap.delete_contact_field
    Delete Contact Field
  • mailtrap.delete_email_template
    Delete Email Template
  • mailtrap.delete_sending_domain
    Delete Sending Domain
  • mailtrap.reset_inbox_credentials
    Reset Inbox Credentials
03 · HOW IT WORKS

Mailtrap in three steps.

  1. 01Your users connect MailtrapThey add their Mailtrap bearer token on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Contact” can wait for the user, and “delete Contact” can be denied outright.
  3. 03Any agent can actYour agent calls Mailtrap 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('mailtrap', {
  read: 'allow',
  write: 'ask',        // create_contact
  destructive: 'deny',  // delete_contact
})

# 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 Mailtrap connects.

Users add their Mailtrap bearer token 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 Mailtrap 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
Bearer token
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Mailtrap from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Mailtrap and Arc0, answered.

Q01

Can I use Mailtrap with Claude, ChatGPT or Cursor?

Yes. Connect Mailtrap 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 Mailtrap actions you allow.

Q02

How do users connect Mailtrap?

Users add their Mailtrap bearer token 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 Mailtrap actions can my agent take?

49 in total: 26 read, 16 write and 7 destructive, such as “create Contact”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Mailtrap?

Yes. Actions like “delete Contact” 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 Mailtrap too?

Yes. The same Mailtrap connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Mailtrap into your agent.

Your users connect Mailtrap once, under your brand. Your agent gets 49 actions behind your policies, with every call on the record.

Connect MailtrapBrowse all apps →

Free to build · MCP + REST · Audit log on every plan