Agenten stärken
Der eigene Befehl des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
npx -y @mailgun/[email protected]Claude Code hat keinen Installationslink für einen lokalen Befehl. Kopieren Sie den Befehl unten und führen Sie ihn in einem Terminal aus.
claude mcp add mailgun-mcp-server -- npx -y @mailgun/mcp-server@2.3.1In einem Terminal ausführen.
{ "mcpServers": { "mailgun-mcp-server": { "command": "npx", "args": [ "-y", "@mailgun/[email protected]" ] } }}claude_desktop_config.json
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenA Model Context Protocol (MCP) server for Mailgun that gives AI agents a practical, workflow-oriented interface to send email, diagnose deliverability, and manage account operations.
[!NOTE] This MCP server runs locally on your machine and communicates over stdio. Mailgun does not currently offer a hosted version of this server.
validate)optimize)inspect)The parenthetical labels above (validate, optimize, inspect) are the product tags used by tag filtering. Every other capability is registered under the send tag.
[!NOTE] Tools are limited to read and update operations — no delete operations are exposed, which keeps the blast radius of an unintended action small. See Security Considerations.
The server is OpenAPI driven. At startup it parses a bundled Mailgun OpenAPI spec and registers a curated allowlist of endpoints as MCP tools, generating each tool's input schema (via Zod) from the spec. Every tool is annotated with a Mailgun product tag (send, validate, optimize, or inspect). All matching tools are registered up front — there is no lazy or on demand loading. Tag filtering is applied at startup to scope which tools get registered, so a given workflow can expose only the products it needs.
The server is published to npm as @mailgun/mcp-server and runs over stdio. Most clients can launch it on demand with npx, so there's nothing to install globally. In each snippet below, replace YOUR-mailgun-api-key with a key from your Mailgun API security settings.
[!TIP] If your account is hosted in Mailgun's EU region, add
"MAILGUN_API_REGION": "eu"to theenvblock (or-e MAILGUN_API_REGION=euon the CLI). It defaults tous.
claude mcp add mailgun -e MAILGUN_API_KEY=YOUR-mailgun-api-key -- npx -y @mailgun/mcp-server
Then run /mcp in Claude Code to confirm the mailgun server is connected.
Open Settings → Developer → Edit Config, or edit the file directly:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%/Claude/claude_desktop_config.json{
"mcpServers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/mcp-server"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key",
"MAILGUN_API_REGION": "us"
}
}
}
}
Open the command palette and choose Cursor Settings → MCP → Add new global MCP server, then add:
{
"mcpServers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/mcp-server"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key"
}
}
}
}
codex mcp add mailgun \
--env MAILGUN_API_KEY=YOUR-mailgun-api-key \
-- npx -y @mailgun/mcp-server
Add the following to your settings.json:
{
"mcp": {
"servers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/mcp-server"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key"
}
}
}
}
}
{
"mcpServers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/mcp-server"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key"
}
}
}
}
Add to ~/.gemini/settings.json:
{
"mcpServers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/mcp-server"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key"
}
}
}
}
Pass flags after the package name in your client's args (e.g. ["-y", "@mailgun/mcp-server", "--tags", "validate,inspect"]).
You can scope which tools the server registers to one or more Mailgun product tags. This is useful for narrowing the toolset shown to the model — for example, only exposing validation tools to a workflow that doesn't need send capabilities.
Valid tags: send, validate, optimize, inspect. When unspecified, every tool is registered (today's default).
Filtering uses OR semantics: a tool is registered if any of its tags appears in the active set.
Via CLI flag — pass --tags in your MCP client config's args:
{
"mcpServers": {
"mailgun": {
"command": "npx",
"args": ["-y", "@mailgun/mcp-server", "--tags", "validate,inspect"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key"
}
}
}
}
Via environment variable — set MAILGUN_MCP_TAGS (CLI flag wins if both are present):
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key",
"MAILGUN_MCP_TAGS": "validate,inspect"
}
[!TIP] Run the binary with
--list-tagsto print supported tag values, or--helpfor full usage. Unknown tags are rejected at startup with a clear error message.
Can you send an email to EMAIL_HERE with a funny email body that makes it sound
like it's from the IT Desk from Office Space? Please use the sending domain
DOMAIN_HERE, and make the email from "postmaster@DOMAIN_HERE"!
[!NOTE] Some MCP clients require a paid plan to invoke tools that send data. If sending fails silently, check your client's plan.
Would you be able to make a chart with email delivery statistics for the past week?
Create a welcome email template for new signups on my domain DOMAIN_HERE.
Include a personalized greeting and a call-to-action button.
Can you check the bounce classification stats for my account and tell me
what the most common bounce reasons are?
Check the DNS verification status for my domain DOMAIN_HERE and tell me
if anything needs fixing.
Are there any unsubscribes or complaints for DOMAIN_HERE? Summarize the
top offenders.
List all my inbound routes and explain what each one does.
Create a mailing list called announcements@DOMAIN_HERE and add these
members: [email protected], [email protected].
Compare my sending volume and delivery rates across all my domains for
the past month.
Break down my email engagement by country and device for DOMAIN_HERE.
List all my domains and show which ones have tracking enabled for clicks
and opens.
Validate the email address EMAIL_HERE and tell me whether it's safe to send to.
Pull the inbox placement results for seed test RESULT_ID_HERE and summarize
where my message landed (inbox, spam, or missing) by provider.
Get the email preview results for test TEST_ID_HERE and tell me if the email
renders correctly across clients.
The server is written in TypeScript. Clone, install, build, and test:
git clone https://github.com/mailgun/mailgun-mcp-server.git
cd mailgun-mcp-server
npm install
npm run build
npm test
npm run build compiles src/ to dist/ and copies the bundled OpenAPI spec. Point your MCP client at the built entry instead of npx (use an absolute path):
{
"mcpServers": {
"mailgun": {
"command": "node",
"args": ["/absolute/path/to/mailgun-mcp-server/dist/mailgun-mcp.js"],
"env": {
"MAILGUN_API_KEY": "YOUR-mailgun-api-key"
}
}
}
}
MCP servers are long-lived stdio processes that don't hot-reload, so the loop is: rebuild on save, then reconnect the client to pick up changes.
Run npm run build once so dist/openapi.yaml is in place.
Keep the TypeScript compiler running to rebuild dist/ on every save:
npx tsc --watch
Point a separate MCP client (or MCP Inspector, below) at dist/mailgun-mcp.js. After a change, restart the MCP client session to load the new build.
The MCP Inspector lets you exercise tools without a full client. Build first, then launch it against the built server:
npm run build
MAILGUN_API_KEY=YOUR-mailgun-api-key npx @modelcontextprotocol/inspector node dist/mailgun-mcp.js
Open the Inspector UI, click Connect, then use List Tools to verify the server is working. To test a filtered toolset, append flags after the server path:
MAILGUN_API_KEY=YOUR-mailgun-api-key npx @modelcontextprotocol/inspector node dist/mailgun-mcp.js --tags validate,inspect
npm install installs a git pre-commit hook (via husky) that runs oxlint --fix and oxfmt on staged TypeScript/JavaScript files and runs npm run check:versions. Fixable issues are auto-fixed and re-staged; commits that introduce unfixable lint errors or version-sync mismatches are rejected. If you already had a local clone before this change, run npm install once to install the hook.
When adding a new endpoint if you use a plain string for it's definition it will default to being tagged with the send product type in the _meta field. If you would like to tag it as a different product use the object version of the EndpointEntry type.
Your Mailgun API key is passed as an environment variable and is never exposed to the AI model itself — it is only used by the MCP server process to authenticate requests. The server does not log API keys, request parameters, or response data.
The server runs locally on your machine. All communication with the Mailgun API is over HTTPS with TLS certificate validation enforced. No data is sent to third-party services beyond the Mailgun API.
Use a dedicated Mailgun API key with permissions scoped to only the operations you need. The server exposes read and update operations but does not expose any delete operations, which limits the blast radius of unintended actions.
The server does not implement client-side rate limiting. Each tool call from the AI translates directly into a Mailgun API request. The server relies on Mailgun's server-side rate limits to prevent abuse — requests that exceed those limits will return an error to the AI assistant.
As with any MCP server, a crafted or adversarial prompt could trick the AI assistant into calling operations you did not intend — for example, modifying tracking settings or reading mailing list members. Review your AI assistant's tool-call confirmations before approving actions, especially in untrusted prompt contexts.
Webhook create and update operations accept arbitrary URLs provided through the AI assistant. The MCP server passes these URLs to the Mailgun API without additional validation. Mailgun is responsible for validating webhook destinations. Ensure your AI assistant does not set webhook URLs to unintended internal or sensitive addresses.
All tool parameters are validated against the Mailgun OpenAPI specification using Zod schemas. However, validation depends on the accuracy of the OpenAPI spec, and some edge-case parameters may fall back to permissive validation. The Mailgun API performs its own server-side validation as an additional layer of protection.
The MCP server communicates over stdio. Refer to the MCP Debugging Guide for troubleshooting.
Apache 2.0 — see LICENSE for details.
We welcome contributions! Please feel free to submit a Pull Request or open an Issue.
An MCP server that gives AI agents a practical interface to Mailgun workflows for sending, diagnosing deliverability, and taking account actions safely.
{ "mcpServers": { "mailgun-mcp-server": { "command": "npx", "args": [ "-y", "@mailgun/[email protected]" ] } }}Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
@mailgun/ läuft lokal über stdio.
Zuletzt geprüft: 2026-11-14. An MCP server that gives AI agents a practical interface to Mailgun workflows for sending, diagnosing deliverability, and taking account actions safely.
