Does my AI agent need a preexisting Gmail or Outlook account to use this?

No. AgentMail is entirely standalone. You can use your agent to programmatically provision brand new, unique email addresses in seconds, completely independent of legacy email providers.

Can my agent download files that users send to its email address?

Yes. When scanning threads in the inbox, your agent will detect any attached files. It can then use the dedicated attachments tool to retrieve and analyze the contents of the file before drafting a reply.

Is it possible to manage multiple outreach campaigns at the same time?

Absolutely. Your agent can create and manage multiple inboxes simultaneously. It can list all active boxes, read unread threads for each, and contextualize its replies based on the specific campaign inbox.

AgentMail MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: AgentMail
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect AgentMail through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to AgentMail "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in AgentMail?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About AgentMail MCP Server

Connect AgentMail to your AI agent and unlock a programmable email client. Stop relying on complex integrations and grant your agent its own functional inbox to communicate with the world.

Pydantic AI validates every AgentMail tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Inboxes — Create, list, and delete custom email addresses on the fly for your agent
Threads — Scan active conversations and read full historical threads natively
Messages — Send new emails, reply contextually to specific threads, and forward messages
Attachments — Extract and process files attached to incoming emails automatically

The AgentMail MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect AgentMail to Pydantic AI via MCP

Follow these steps to integrate the AgentMail MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from AgentMail with type-safe schemas

Why Use Pydantic AI with the AgentMail MCP Server

Pydantic AI provides unique advantages when paired with AgentMail through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your AgentMail integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your AgentMail connection logic from agent behavior for testable, maintainable code

AgentMail + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the AgentMail MCP Server delivers measurable value.

Type-safe data pipelines: query AgentMail with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple AgentMail tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query AgentMail and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock AgentMail responses and write comprehensive agent tests

AgentMail MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect AgentMail to Pydantic AI via MCP:

create_inbox

You can optionally link it to a custom domain. Create a new email inbox for an agent

delete_inbox

Warning: this deletes all emails in it. Delete a specific inbox by ID

forward_message

You can optionally add text to the forwarded message. Forward an existing email message

get_attachment

Attachments might be encoded in base64. Ensure you parse or read it correctly. Download or read a specific attachment from a message

get_inbox

Get details of a specific inbox by ID

get_thread

Requires a thread_id. Read all messages inside a specific conversation thread

list_inboxes

An inbox is required to send or receive emails. Returns an array of inboxes with their IDs, email addresses, and names. List all inboxes assigned to the AgentMail API Key

list_threads

Returns a list of thread objects including subject lines and recent message previews. The agent needs an inbox_id first. List conversation threads inside an inbox

reply_to_message

The thread will be preserved. Reply to an existing email message/thread

send_message

Requires the sender inbox_id, which you can get from list_inboxes. Send a brand new email message

update_message

Update an existing message metadata (like marking it as read)

Example Prompts for AgentMail in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with AgentMail immediately.

"Create a new inbox for our support team."

"Check all my unread threads in the main inbox today."

"Reply to the client thanking them and attach the pricing PDF."

Troubleshooting AgentMail MCP Server with Pydantic AI

Common issues when connecting AgentMail to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

AgentMail + Pydantic AI FAQ

Common questions about integrating AgentMail MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your AgentMail MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.