How to Use the Mailosaur MCP in AutoGen

Q: Can an AutoGen agent create a new Mailosaur server dynamically?

Yes. An agent can call createvirtualserver to provision a clean inbox at the start of a conversation, registering the tool via the MCP setup. It then shares the new server details with other agents in the group chat.

Q: How do I find the correct server ID for my tests?

You use listvirtualservers to list all available inboxes and their IDs. Your agent can search this list for a specific server name to find the correct ID for the test run.

Build multi-agent AutoGen teams that debate and verify email and SMS workflows using Mailosaur.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailosaur MCP to AutoGen

Create your Vinkius account to connect Mailosaur 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 Mailosaur with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent validation using AutoGen and Mailosaur

The `search_server_messages` tool allows your AutoGen agents to find specific verification emails and debate their validity using the MCP connection. One agent can retrieve the message while another checks if the HTML layout matches the design system. They discuss the results in a chat loop to reach a consensus before passing the build. This collaborative approach eliminates single-point-of-failure scripts. By letting specialized agents analyze different aspects of the same email, you catch both visual regressions and broken links in a single pass.

Dynamic inbox provisioning for agent workflows

The `create_virtual_server` tool gives your AutoGen coordinator agent the ability to spin up isolated testing environments on demand. When a new test scenario begins, the coordinator creates a fresh inbox and passes the server ID to the worker agents. This keeps parallel testing tracks completely isolated. After the test scenario wraps up, the coordinator uses `clear_server_inbox` to wipe the environment clean. This keeps subsequent agent conversations clean without needing extra MCP tools.

Deep content inspection with AutoGen agents

The `get_message_content` tool is used by your verification agents to pull the raw HTML and text bodies of transactional messages. Agents can inspect links, extract tokens, and verify that dynamic fields like usernames are rendered correctly. They can then cross-reference this data with external API responses to ensure absolute accuracy. If a specific message is flagged as corrupt or incorrect, the agent can use `delete_specific_message` to remove it and trigger a retry. This ensures your test suite can self-heal and recover from transient network blips without manual intervention.

Setup guide

Set up Mailosaur 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 Mailosaur 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="Mailosaur_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent triggers the signup action, while a second agent uses `search_server_messages` to look for the verification email. Once found, the second agent extracts the link and passes it back to the first agent to complete the registration.

Yes. An agent can call `create_virtual_server` to provision a clean inbox at the start of a conversation, registering the tool via the MCP setup. It then shares the new server details with other agents in the group chat.

You can configure your agents to use backoff strategies between calls to `list_server_messages`. The coordinating agent can monitor tool outputs and instruct the polling agent to wait if rate limits are approached.

You use `list_virtual_servers` to list all available inboxes and their IDs. Your agent can search this list for a specific server name to find the correct ID for the test run.

No. All communication with the Mailosaur API occurs over encrypted HTTPS connections initiated by the MCP Server. Your raw email body text, SMS verification codes, and server configuration details remain inside your private local environment.

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