How to Use the Mailgun (Transactional Email & Domains) MCP in Pydantic AI

Q: How do I initialize the Mailgun (Transactional Email & Domains) MCP Server in pydantic-ai?

Import MCPToolset from the framework and pass the HTTP endpoint URL. Register this toolset when instantiating your agent to expose the email and domain tools.

Q: Does pydantic-ai validate the email addresses checked by Mailgun (Transactional Email & Domains)?

Yes. When the agent calls validateemail, the response is parsed against a strict schema. The agent can instantly verify if the email is deliverable before attempting to send.

Q: Can I use this server to check my DNS setup?

Yes. The agent uses listdomains to find your configured domains and getdomain to check their active DNS records, helping you catch configuration errors early.

Build type-safe email workflows with Pydantic AI and Mailgun to guarantee zero silent runtime failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailgun (Transactional Email & Domains) MCP to Pydantic AI

Create your Vinkius account to connect Mailgun (Transactional Email & Domains) to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Mailgun (Transactional Email & Domains) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Send transactional emails with strict type safety

The `send_email` tool lets your agent send transactional messages with guaranteed payload validation. Because Pydantic AI validates every input and output at runtime, your agent cannot pass malformed recipient fields or invalid HTML templates to the Mailgun API. If the agent attempts to send an email with missing required fields, the framework raises a validation error immediately. This prevents broken API calls from silently failing in your production environment.

Clean bounce lists with runtime validation

The `list_bounces` tool retrieves hard bounce records that your agent parses into strongly typed Python objects. The agent can safely inspect the bounce reasons and call `delete_bounce` to remove stale records without risking type mismatch errors. It also tracks user preferences using `list_unsubscribes`. This ensures your internal unsubscribe database stays perfectly synced with Mailgun's suppression lists.

Validate domain metrics using this MCP Server

The `get_stats` tool pulls historical delivery metrics directly into your type-safe agent. The server converts the raw JSON response into structured data, allowing your agent to evaluate open rates and spam complaints without parsing errors. If you need deeper event-level details, the agent uses `list_logs` to fetch raw delivery and drop events. This gives you a clear audit trail of every message sent through your domain.

Setup guide

Set up Mailgun (Transactional Email & Domains) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "mailgun-transactional-email-domains-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Mailgun (Transactional Email & Domains) tools.",
)

result = await agent.run("List recent Mailgun (Transactional Email & Domains) transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mailgun. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Mailgun (Transactional Email & Domains) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Mailgun (Transactional Email & Domains) MCP in Pydantic AI

Import `MCPToolset` from the framework and pass the HTTP endpoint URL. Register this toolset when instantiating your agent to expose the email and domain tools.

Yes. When the agent calls `validate_email`, the response is parsed against a strict schema. The agent can instantly verify if the email is deliverable before attempting to send.

The framework will raise a validation error. This prevents the agent from operating on corrupted or incomplete API responses, ensuring absolute correctness in your data pipeline.

Yes. The agent uses `list_domains` to find your configured domains and `get_domain` to check their active DNS records, helping you catch configuration errors early.

The server runs in an isolated V8 sandbox with strict zero-trust policies. Your API keys are injected securely at runtime and are never logged, stored, or exposed to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript