Postmark MCP server
19 operations0 webhooks
Transactional email API for sending single and batch messages, managing templates and streams, and reading delivery statistics.
Try Postmark with your agent
Connect Postmark, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in Postmark on my account, then run one read-only example and show me the result.
Postmark tools and triggers
Tools are what your agent can do in Postmark through Corsair's MCP server. Triggers are the Postmark events a routine can start from.
Templates
- CreateWrite
Create a standard or layout template
templates.create
- DeleteDestructive
Delete a template. Sends already made with it are unaffected, but it cannot be restored
templates.delete
- GetRead-only
Read one template by id or alias
templates.get
- ListRead-only
List the templates on this server, paged by `Count` and `Offset`
templates.list
- UpdateWrite
Change a template's name, subject, bodies or alias
templates.update
- ValidateRead-only
Render a template against a model and report whether its subject and bodies are valid
templates.validate
Bounces
- ActivateWrite
Reactivate an address Postmark deactivated after a bounce. A hard bounce that cannot be reactivated reports so
bounces.activate
- DeliveryRead-only
Read delivery statistics broken down by bounce type
bounces.delivery
- GetRead-only
Read one bounce by its numeric id
bounces.get
- ListRead-only
List bounces filtered by type, address, tag, message or date window
bounces.list
Streams
- ArchiveDestructive
Archive a message stream, after which it can no longer send. The default transactional and inbound streams cannot be archived
streams.archive
- GetRead-only
Read one message stream
streams.get
- ListRead-only
List the message streams on this server
streams.list
- SendDestructive
Send one transactional email. This delivers a real message and cannot be recalled once Postmark accepts it
email.send
- Send BatchDestructive
Send up to 500 emails in one request. The response is a per-message result list, and a 200 does not mean every message was sent
email.sendBatch
Server
- GetRead-only
Read this server's settings, including its delivery type and whether SMTP is on
server.get
- UpdateWrite
Change server settings such as tracking, hook URLs and the inbound spam threshold
server.update
Stats
- OverviewRead-only
Read the outbound overview: sends, opens, clicks, bounces and spam complaints with their rates
stats.overview
- SendsRead-only
Read the daily sent count over a date window
stats.sends
Connect Postmark to Claude, ChatGPT or Cursor
- 1
Connect Postmark in Corsair
Add your Postmark API key once in Corsair. Corsair stores the credential encrypted and makes the Postmark API calls for your agent, so it never goes into a prompt or a config file. Connect Postmark
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Postmark. On a ChatGPT personal plan, connect Postmark here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Postmark's read and write operations run right away and its 4 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/postmark, add the Postmark plugin, and connect with an API key. Then call methods like corsair.postmark.api.bounces.activate() from your app. Corsair keeps each tenant isolated.
Yes. Postmark requires an API key from your Postmark account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit Postmark, GitHub, Notion, Stripe, and the rest. Trigger Postmark from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for transactional email API for sending single and batch messages, managing templates and streams, and reading delivery statistics. Common builds include sync jobs, admin tooling, and agents that call Postmark APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Postmark API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/postmark in the open repo. When Postmark ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your Postmark data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Postmark data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put Postmark on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 4 destructive Postmark operations. You can change a link's mode at hub.corsair.dev/me.