MailerSend for AI agents
MailerSend is a transactional email and SMS service developers use to send, track, and manage programmatic messages triggered by application events. 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 MailerSend.
Check sent message activity
Pull recent sent messages and their delivery status for a customer's transactional emails, read-only.
Check remaining API quota
Look up the account's sending quota before triggering a large batch of transactional emails.
Approve before deleting a domain
Require approval before deleting a sending domain, since it would stop outgoing mail from that domain.
23 MailerSend actions, graded by risk.
Every MailerSend action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
18Look things up. Allowed by default.
- mailersend.get_usersGet users
- mailersend.get_domainGet Domain
- mailersend.get_tokensGet API Tokens
- mailersend.get_domainsGet sending domains
- mailersend.get_messagesGet sent messages
- mailersend.get_webhooksList webhooks
- mailersend.get_api_quotaGet API Quota
- mailersend.get_templatesGet email templates
- mailersend.get_identitiesList Sender Identities
- mailersend.get_recipientsGet email recipients
- mailersend.get_smtp_usersGet SMTP users
- mailersend.get_sms_numbersGet SMS Numbers
- mailersend.get_sms_activityGet SMS Activity
- mailersend.get_sms_inboundsGet SMS Inbounds
- mailersend.get_sms_messagesList SMS Messages
- mailersend.get_sms_recipientsGet SMS recipients
write
4Create and change things. Allow, or ask the user first.
- mailersend.create_tokenCreate API Token
- mailersend.create_domainCreate Sending Domain
- mailersend.create_webhookCreate Webhook
- mailersend.create_smtp_userCreate SMTP User
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- mailersend.delete_webhookDelete Webhook
MailerSend in three steps.
- 01Your users connect MailerSendThey add their MailerSend api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create API Token” can wait for the user, and “delete Webhook” can be denied outright.
- 03Any agent can actYour agent calls MailerSend through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mailersend', { read: 'allow', write: 'ask', // create_token destructive: 'deny', // delete_webhook }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How MailerSend connects.
Users add their MailerSend 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 MailerSend 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 MailerSend from any agent.
MailerSend and Arc0, answered.
Can I use MailerSend with Claude, ChatGPT or Cursor?
Yes. Connect MailerSend 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 MailerSend actions you allow.
How do users connect MailerSend?
Users add their MailerSend 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 MailerSend actions can my agent take?
23 in total: 18 read, 4 write and 1 destructive, such as “create API Token”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in MailerSend?
Yes. Actions like “delete Webhook” 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 MailerSend too?
Yes. The same MailerSend connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug MailerSend into your agent.
Your users connect MailerSend once, under your brand. Your agent gets 23 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan