How to Use the AgentMail MCP in Pydantic AI

Q: What's the setup process for AgentMail with Pydantic AI?

It's straightforward. After installing pydantic-ai-slimmcp, you instantiate an MCPToolset with your Vinkius server URL. Then you just pass that toolset into your Agent's toolsets list.

Add type-safe, validated email tools to your Pydantic AI agent. No more guessing what the API returned.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentMail MCP to Pydantic AI

Create your Vinkius account to connect AgentMail 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 AgentMail with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inboxes That Match Your Models

Your agent gets reliable email tools. It can `create_inbox` for a new task or `list_inboxes` to see what it already controls. The key is that the output of these tools is always a Pydantic model. If the AgentMail server ever returns data that doesn't match the expected schema—say, a malformed inbox object—your Pydantic AI agent will raise a `ValidationError` immediately. You get correctness by default, preventing bad data from propagating through your system.

Validate Every Incoming Email

Let your agent read email without worrying about data integrity. It uses `list_threads` and `get_thread` to pull conversations. Every message, every subject line, every sender is parsed into a Pydantic model. This is huge when dealing with attachments via `get_attachment`. Your agent knows exactly what data type to expect for the file content and filename. No more silent failures or downstream bugs because an API field was unexpectedly null.

Type-Safe Email Sending via MCP Server

Your Pydantic AI agent can send and manage email with structured calls. It uses `send_message` for new emails and `reply_to_message` to continue a thread. The inputs to these functions are also validated. You define the `Message` model, and Pydantic AI ensures your agent provides all the required fields before it even attempts the API call. This approach catches logic errors in your agent's code early, long before it sends a broken email. This MCP server just works with it.

Setup guide

Set up AgentMail 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": {
        "agentmail-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent AgentMail 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 AgentMail. 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 AgentMail 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 AgentMail MCP in Pydantic AI

Pydantic AI validates both the data sent to and received from the AgentMail tools. When your agent calls `send_message`, Pydantic AI checks that all required parameters are there. When AgentMail responds, it validates the response against your defined Pydantic models, crashing loudly if there's a mismatch.

It's straightforward. After installing `pydantic-ai-slim[mcp]`, you instantiate an `MCPToolset` with your Vinkius server URL. Then you just pass that toolset into your `Agent`'s `toolsets` list.

Yes, Pydantic AI is model-agnostic. You can use OpenAI, Anthropic, Gemini, or a local model. AgentMail provides the email tools, and Pydantic AI ensures that whatever LLM you choose uses them correctly and gets validated data back.

You can create a custom toolset that only includes the read-only functions from the MCP server, like `list_threads` and `get_thread`. Pydantic AI gives you the control to define exactly which tools are available to the agent.

Your email message content, headers, and attachments are processed by the AgentMail service to fulfill your agent's requests. This data flows through a zero-trust, ephemeral sandbox on our end. Vinkius does not persist your email data; it's only held for the duration of the operation.

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