How to Use the Mailtrap MCP in AutoGen

Q: Can AutoGen agents switch between Mailtrap projects?

They can. Using listmailtrapprojects, your agents can identify the correct environment and then perform operations within that specific project scope.

Let your AutoGen agents debate email testing strategies and verify delivery using the Mailtrap MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailtrap MCP to AutoGen

Create your Vinkius account to connect Mailtrap 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 Mailtrap with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable multi-agent debate on email quality

Deploy a quality-assurance agent that uses `list_sandbox_messages` to inspect new emails. If it finds issues, it can trigger a debate with a developer agent to resolve rendering bugs. This creates a feedback loop where agents critique each other's work. The consensus is reached only after the email passes your defined validation checks.

Automate production releases with AutoGen

Have your release manager agent call `send_production_email` only after a verification agent confirms the test version matches the expected HTML from `get_message_html`. The agents must agree on the test results before any live email is triggered. It adds a layer of logic that prevents broken layouts from reaching production.

Manage sandbox state through agent consensus

Configure your agents to collectively decide when to run `clear_sandbox_inbox`. This ensures your testing environment stays clean without human intervention. They coordinate the timing of the cleanup to avoid interrupting active tests. It keeps your workspace organized through automated, deliberative action.

Setup guide

Set up Mailtrap 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 Mailtrap 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="Mailtrap_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Mailtrap 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="Mailtrap_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Mailtrap 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 Mailtrap. 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 Mailtrap 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 Mailtrap MCP in AutoGen

AutoGen agents treat the Mailtrap tools as skills. They can call `send_test_email` or `list_sandbox_messages` during their conversation to gather the information needed to make decisions.

Yes. You can filter the tool list passed to your AssistantAgent. For example, only provide `send_production_email` to agents specifically authorized for deployment tasks.

The server runs in an isolated Vinkius sandbox. Your email payloads are never stored on the agent host, and credentials are handled through a single secure endpoint token.

They continue the debate until they reach a state that satisfies the criteria. You can view the conversation logs to see exactly why they chose to call or ignore a specific tool.

They can. Using `list_mailtrap_projects`, your agents can identify the correct environment and then perform operations within that specific project scope.

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