How to Use the Mailosaur MCP in OpenAI Agents SDK

Q: Can the agent handle multiple Mailosaur servers at once?

Yes. The agent calls listvirtualservers to identify available server IDs. You can configure handoffs between specialized agents, where one agent provisions the server and another handles the actual message verification.

Q: What happens if the agent fails to find an email?

The searchservermessages tool returns an empty result set. The OpenAI Agents SDK logs this interaction in your tracing dashboard, allowing you to debug whether the issue was a slow email delivery or a broken test flow.

Run automated email verification workflows safely in production using the OpenAI Agents SDK and 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 OpenAI Agents SDK

Create your Vinkius account to connect Mailosaur to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Isolate Tests with Mailosaur MCP Server

The `create_virtual_server` tool lets your agent provision isolated testing environments on demand. When your OpenAI agent needs to test a password reset flow, it spins up a fresh inbox without stepping on other concurrent test runs. You configure the agent with strict guardrails to ensure it only acts within its designated virtual server. By calling `get_server_details`, the agent verifies the environment properties before proceeding, keeping your production test suite isolated and traceable on the OpenAI dashboard.

Read and Verify Message Payloads

Your agent uses `get_message_content` to pull down the exact HTML or plain text of an email. Instead of writing brittle regex patterns, you hand the raw payload to the agent and let it validate the content against your expected test outcomes. When testing complex workflows, the agent relies on `search_server_messages` to find specific emails by sender or subject. If an expected SMS doesn't arrive, the agent catches the failure immediately and logs the exact missing criteria in your OpenAI tracing interface.

Maintain Ephemeral Test States

The `delete_specific_message` tool gives your agent the ability to clean up after itself once a test passes. Your automated pipelines stay fast because the agent actively manages inbox size rather than letting test data accumulate over time. For broader teardowns, the agent triggers `clear_server_inbox` to wipe the entire virtual server between test suites. You monitor these destructive actions through the OpenAI Agents SDK guardrails, ensuring the agent never deletes data outside the intended scope.

Setup guide

Set up Mailosaur MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Mailosaur tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mailosaur tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mailosaur tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Mailosaur Agent",
            instructions="You have access to Mailosaur tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the openai-agents package via pip. You initialize the connection using MCPServerStreamableHttp and pass the Mailosaur MCP Server URL. The agent auto-discovers the email testing tools immediately.

Yes. The agent calls list_virtual_servers to identify available server IDs. You can configure handoffs between specialized agents, where one agent provisions the server and another handles the actual message verification.

Set cacheToolsList=True when configuring your OpenAI agent. This prevents the agent from re-fetching the eight available Mailosaur tools on every execution loop, significantly dropping your execution latency.

The search_server_messages tool returns an empty result set. The OpenAI Agents SDK logs this interaction in your tracing dashboard, allowing you to debug whether the issue was a slow email delivery or a broken test flow.

This server accesses raw email bodies, SMS payloads, and sender metadata. Vinkius runs the MCP Server in an ephemeral V8 Isolate Sandbox with zero-trust architecture, meaning your test authentication links and one-time passwords are destroyed the moment the session ends.

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