How to Use the MailSlurp MCP in OpenAI Agents SDK

Q: How do I connect MailSlurp to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint URL and pass it to the mcpservers array in your Agent constructor. Set cacheToolsList=True to speed up initialization.

Q: Can the OpenAI Agents SDK read attachments with MailSlurp?

Yes, the agent uses the getemaildetails tool to pull the complete message payload. You can parse the returned data to verify attachment names and sizes during your automated tests.

Q: How do I list active inboxes using MailSlurp and the OpenAI Agents SDK?

The agent executes listallinboxes to pull an array of your current email endpoints. You can also filter specific messages within those addresses by calling listinboxemails.

Build production-ready email testing workflows using MailSlurp and the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MailSlurp MCP to OpenAI Agents SDK

Create your Vinkius account to connect MailSlurp 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 MailSlurp with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate inboxes via OpenAI Agents SDK

The `create_random_inbox` tool generates disposable email addresses on demand for your agent. This MCP server lets you spin up isolated endpoints to test user registration flows without touching real accounts. Your OpenAI agent handles the provisioning and automatically tracks the generated credentials. When the test concludes, the agent calls `delete_specific_inbox` to clear the resources. This prevents stale data from polluting your testing environment. Built-in guardrails ensure the agent only deletes the exact inbox it just created.

Verify asynchronous message delivery

The `wait_for_latest_email` tool pauses your workflow until a specific message hits the inbox. Instead of writing custom retry loops, your agent just long-polls the endpoint. It grabs the incoming verification code or password reset link the second it arrives. For batch operations, `wait_for_email_count` verifies that a precise number of messages landed successfully. You combine this with the OpenAI dashboard tracing to see exactly how long your backend takes to dispatch transactional emails.

Inspect headers and send replies

Using `get_email_details`, this MCP integration extracts the raw HTML, attachments, and headers from any received message. Your agent parses this payload to confirm CSS rendering or check for missing variables in the template. Testing two-way communication requires the `send_email_from_inbox` command. The agent fires a reply right back to your application, completing the loop. You get a full end-to-end test of your inbound parsing logic without leaving the Python ecosystem.

Setup guide

Set up MailSlurp 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 MailSlurp tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MailSlurp 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="MailSlurp Agent",
            instructions="You have access to MailSlurp 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 MailSlurp. 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 MailSlurp 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 MailSlurp MCP in OpenAI Agents SDK

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius endpoint URL and pass it to the `mcp_servers` array in your Agent constructor. Set `cacheToolsList=True` to speed up initialization.

Yes, the agent uses the `get_email_details` tool to pull the complete message payload. You can parse the returned data to verify attachment names and sizes during your automated tests.

You set the timeout parameters directly when calling the wait tools. If `wait_for_latest_email` exceeds the limit, the agent catches the error and can trigger a fallback action or fail the test gracefully.

The agent executes `list_all_inboxes` to pull an array of your current email endpoints. You can also filter specific messages within those addresses by calling `list_inbox_emails`.

This integration processes raw email bodies, sender addresses, and attachments. The Vinkius V8 Isolate Sandbox destroys the execution environment immediately after the agent finishes the task, leaving no persistent memory of your test data.

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