How to Use the AgentMail MCP in AutoGen

Q: How do I configure the AgentMail MCP Server in AutoGen?

Install autogen-extmcp first. You use mcpservertools with StreamableHttpServerParams pointing to your Vinkius endpoint, then pass the resulting list to your AssistantAgent.

Q: Can multiple AutoGen agents share the same AgentMail inbox?

They share the tools, so any agent with access can run getinbox or sendmessage. You usually assign the email tools to a single execution agent while the others handle reasoning.

Q: Can AutoGen agents delete an AgentMail inbox automatically?

Yes, if you give them permission. An agent can call deleteinbox to wipe the address and all stored messages once a specific project concludes.

Equip your AutoGen multi-agent squads with real email inboxes to negotiate, draft, and send messages.

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 AutoGen

Create your Vinkius account to connect AgentMail to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Attach the AgentMail MCP Server to AutoGen squads

Multi-agent systems need a way to communicate with the outside world. You hook up the `agentmail-mcp` tools, and your primary communication agent runs `create_inbox` to provision a custom address immediately. The rest of the squad uses that address to interact with human users. A support agent monitors incoming traffic using `list_threads`, pulling fresh complaints into the group chat for the other agents to analyze.

Debate email drafts before sending

You do not want a single LLM firing off raw emails to your clients. A drafting agent writes a proposed response and shares it in the AutoGen conversation. A secondary compliance agent reviews the text, suggests edits, and forces a rewrite. They argue until they reach a consensus. Once the compliance agent approves the final copy, the execution agent triggers `reply_to_message` to send the sanitized email. You get the safety of peer review without human intervention.

Triage and route complex attachments

Incoming files often require different specialists. When a message arrives with a payload, a triage agent runs `get_attachment` to download the base64 data. It decodes the file and looks at the contents. If the file is a legal contract, the triage agent tags the legal analysis agent. If it is a technical spec, it wakes up the engineering agent. They process the document and collectively decide whether to `forward_message` to a specific human department.

Setup guide

Set up AgentMail MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AgentMail tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AgentMail_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AgentMail data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AgentMail_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AgentMail data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` first. You use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius endpoint, then pass the resulting list to your `AssistantAgent`.

They share the tools, so any agent with access can run `get_inbox` or `send_message`. You usually assign the email tools to a single execution agent while the others handle reasoning.

AutoGen converts the JSON schema from the server into native Python types automatically. Your agents see standard function signatures for tools like `update_message` and `list_inboxes`.

Yes, if you give them permission. An agent can call `delete_inbox` to wipe the address and all stored messages once a specific project concludes.

Vinkius manages the underlying MCP server via an ephemeral, zero-trust architecture. When your agents pull thread subjects or parse base64 attachments, the transport layer discards the data immediately after delivery.

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