How to Use the Mailinator MCP in OpenAI Agents SDK

Q: How do I initialize the Mailinator MCP Server in my OpenAI Agents SDK pipeline?

Install the package using pip install openai-agents and configure the HTTP streamable server parameters. Pass the Vinkius URL inside MCPServerStreamableHttpParams using an async with context manager and add the server to your agent constructor via mcpservers=server. Setting cacheToolsList=True ensures fast startup times by caching the Mailinator tool definitions.

Q: Can an OpenAI Agents SDK agent automatically clean up test messages via Mailinator?

Yes, your agent can call removemessage once it finishes verifying an email workflow. This keeps your private staging domains clean during high-volume parallel test runs. You can trace this delete action directly inside the OpenAI developer dashboard.

Q: How does the OpenAI Agents SDK handle rate limits when querying Mailinator statistics?

Your agent can monitor usage by calling getusagestatistics to prevent hitting plan thresholds. If limits are reached, the SDK's built-in execution loop handles the pause, or you can program a specialized agent to throttle requests.

Q: Can I route SMS verifications to my OpenAI Agents SDK workflows?

Yes, the agent can call listprivatesms to pull verification codes sent via SMS to your private numbers. This allows the OpenAI Agents SDK to test multi-factor authentication flows alongside standard email verification.

Run end-to-end email testing directly inside your OpenAI Agents SDK pipeline without managing mock SMTP servers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mailinator MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Email Assertions in OpenAI Agents SDK

The Mailinator MCP Server exposes `list_inbox_messages` directly to your OpenAI agent pool to verify receipt of transactional emails. By calling `get_message_content` to read the test email body, the agent extracts activation codes to complete signup flows while streaming the raw text directly into your OpenAI agent context. The entire interaction traces directly on your OpenAI developer dashboard, letting you watch the agent handle Mailinator verification emails in real time.

Secure Link Extraction with Agent Guardrails

Your OpenAI agent uses `extract_message_links` to pull reset links from ephemeral messages, running under your defined SDK safety constraints. This prevents the agent from clicking malicious or unverified third-party URLs during automated test runs. You configure these OpenAI guardrails directly inside your Python codebase, ensuring the agent only processes Mailinator links matching your staging domains.

Simulate Traffic and Handoff to QA Agents

Trigger realistic test scenarios by having your system run `inject_test_message` to populate mock inboxes with specific payloads for your OpenAI agent. This multi-agent setup runs natively within the SDK, passing the Mailinator message ID so a secondary agent can run `list_message_attachments` to process payloads. You manage this secure multi-agent workflow using a single connection token from Vinkius, keeping your testing pipeline completely isolated.

Setup guide

Set up Mailinator 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 Mailinator tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using `pip install openai-agents` and configure the HTTP streamable server parameters. Pass the Vinkius URL inside `MCPServerStreamableHttpParams` using an `async with` context manager and add the server to your agent constructor via `mcp_servers=[server]`. Setting `cacheToolsList=True` ensures fast startup times by caching the Mailinator tool definitions.

Yes, your agent can call `remove_message` once it finishes verifying an email workflow. This keeps your private staging domains clean during high-volume parallel test runs. You can trace this delete action directly inside the OpenAI developer dashboard.

Your agent can monitor usage by calling `get_usage_statistics` to prevent hitting plan thresholds. If limits are reached, the SDK's built-in execution loop handles the pause, or you can program a specialized agent to throttle requests.

Yes, the agent can call `list_private_sms` to pull verification codes sent via SMS to your private numbers. This allows the OpenAI Agents SDK to test multi-factor authentication flows alongside standard email verification.

Your email content and attachments are processed inside an ephemeral, zero-trust V8 Isolate Sandbox on Vinkius via our hosted MCP Server. No data is stored on Vinkius servers after the execution completes, ensuring your staging emails remain private.

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