Postmark for AI agents

Postmark is a transactional email delivery service known for high deliverability and detailed sending analytics. Developers use it to send receipts, password resets, and notifications reliably. 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 Postmark See the 46 actions ↓

EmailAPI keyMCP + RESTpostmarkapp.com

AUDIT LOG · POSTMARKPOLICY: acme-support

09:41:07 · claude · u_8f2read

postmark.list_webhooks

List Webhooks✓ allowed · 212ms

09:41:08 · claude · u_8f2read

postmark.get_server

Get Server✓ allowed · 164ms

09:41:09 · claude · u_8f2write

postmark.create_webhook

Create Webhook✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

postmark.delete_webhook

Delete Webhook✕ blocked · policy: deny

EVERY POSTMARK CALL, ON THE RECORD

01 · USE CASES

What agents do in Postmark.

Check delivery stats read-only

Pull delivery statistics for a message stream to confirm emails are reaching inboxes.

Check spam complaints

Look up recent spam complaints read-only to catch a deliverability problem early.

Create a suppression with approval

Add an email to the suppression list only after confirming the recipient opted out.

02 · ACTIONS

46 Postmark actions, graded by risk.

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

read

Look things up. Allowed by default.

postmark.get_server
Get Server
postmark.get_bounces
Get Bounces
postmark.get_webhook
Get Webhook
postmark.get_template
Get Template
postmark.list_webhooks
List Webhooks
postmark.list_templates
List Templates
postmark.get_sent_counts
Get Sent Counts
postmark.get_click_counts
Get Click Counts
postmark.get_bounce_counts
Get Bounce Counts
postmark.get_browser_usage
Get Browser Usage
postmark.list_suppressions
List Suppressions
postmark.get_delivery_stats
Get Delivery Stats
postmark.get_message_stream
Get Message Stream
postmark.list_inbound_rules
List Inbound Rules
postmark.get_spam_complaints
Get Spam Complaints
postmark.list_message_streams
List Message Streams

+ 14 MORE

write

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

postmark.create_webhook
Create Webhook
postmark.create_template
Create Template
postmark.create_inbound_rule
Create Inbound Rule
postmark.create_suppressions
Create Suppressions
postmark.create_message_stream
Create Message Stream
postmark.update_message_stream
Update Message Stream
postmark.send_batch_with_templates
Send Batch Templated Emails
postmark.edit_server
Edit Server
postmark.edit_webhook
Edit Webhook
postmark.edit_template
Edit Template
postmark.unarchive_message_stream
Unarchive Message Stream

destructive

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

postmark.delete_webhook
Delete Webhook
postmark.delete_template
Delete Template
postmark.delete_inbound_rule
Delete Inbound Rule
postmark.delete_suppressions
Delete Suppressions
postmark.archive_message_stream
Archive Message Stream

03 · HOW IT WORKS

Postmark in three steps.

01Your users connect PostmarkThey add their Postmark api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Webhook” can wait for the user, and “delete Webhook” can be denied outright.
03Any agent can actYour agent calls Postmark 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('postmark', {
  read: 'allow',
  write: 'ask',        // create_webhook
  destructive: 'deny',  // delete_webhook
})

# 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 Postmark connects.

Users add their Postmark 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 Postmark 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 Postmark from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More email apps.

Elastic Email91 actions

Resend66 actions Lettr60 actions

Missive40 actions

ALL EMAIL APPS →

07 · FAQ

Postmark and Arc0, answered.

Q01

Can I use Postmark with Claude, ChatGPT or Cursor?

Yes. Connect Postmark 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 Postmark actions you allow.

Q02

How do users connect Postmark?

Users add their Postmark 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 Postmark actions can my agent take?

46 in total: 30 read, 11 write and 5 destructive, such as “create Webhook”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Postmark?

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.

Q05

Can my own backend call Postmark too?

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

Get started

Plug Postmark into your agent.

Your users connect Postmark once, under your brand. Your agent gets 46 actions behind your policies, with every call on the record.

Connect Postmark Browse all apps →

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