Skip to content
Custom Connectors
SolutionsConnectorsPricingResourcesBlog
Build my connector

Connect Mailgun to Claude Code

Let Claude send mail and manage lists and suppressions in Mailgun. From the terminal, inside the sessions where you already work.

Build my connectorTalk to us

How do you connect Mailgun to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Mailgun, you add a Mailgun MCP server: a small hosted service that exposes Mailgun's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Mailgun account. No API keys pasted into config files.

claude mcp add --transport http mailgun https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Mailgun once connected?

Full read-write Mailgun access lets Claude send a message through a sending domain, add or remove mailing list members, add or clear suppression entries like bounces and unsubscribes, and pull delivery events into a summary. The triage and list cleanup that meant juggling the dashboard and API happen in one place.

  • Send a transactional or test message through an authorized sending domain
  • Add, update, or remove members on a Mailgun mailing list
  • Add or clear suppression entries for bounces, unsubscribes, and complaints
  • Summarize delivery, open, and failure events for a recent send
  • Create or rotate a route to forward inbound mail to the right place
  • Validate an address before adding it to a list

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Mailgun access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Mailgun API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Mailgun changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Mailgun connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Mailgun connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Mailgun account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Mailgun's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Mailgun?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Mailgun account it signs in with. Revoking access is one click in Mailgun.

More on the Mailgun connector

Mailgun connector for claude.aiTelegram + Claude CodeWhatsApp Business + Claude CodeWebex + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connectorTalk to us