How to Use the Maileon MCP in OpenAI Agents SDK

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

Install openai-agents and initialize MCPServerStreamableHttp with your Vinkius MCP Server endpoint URL. Pass this server instance inside the mcpservers list when creating your Agent constructor to let the model auto-discover all nine marketing tools.

Q: Can OpenAI Agents SDK run Maileon double opt-ins?

Yes, calling createnewcontact automatically triggers your pre-configured double opt-in flow on the server side. The agent only needs to send the email address and contact fields to start the validation sequence.

Q: How can my agent check why a mailing failed to send?

Your agent runs getmailingdetails to check the current state and configuration of the campaign. If the server shows the campaign is still in a draft state, you must set it to ready before calling the dispatch tool.

Run safe, production-grade email marketing agents with OpenAI Agents SDK and our verified Maileon MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maileon MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync contacts via OpenAI Agents SDK

The `create_new_contact` tool registers new subscribers directly into your Maileon database while initiating the configured double opt-in process. Your agents handle incoming sign-up webhooks, validate the payload format, and pass clean data straight to your list without manual steps. For clean list maintenance, `delete_account_contact` removes users who request complete deletion through your support agent. Using this tool prevents compliance errors by immediately purging records instead of waiting for weekly batch jobs.

Automate campaigns using this MCP Server

The `dispatch_email_mailing` tool triggers the delivery of prepared campaigns once they reach a ready state in your account. OpenAI agents verify that all sending conditions are met before executing the dispatch, preventing accidental drafts from going live. To select the correct campaign, the agent calls `list_email_mailings` to filter drafts by state or date. This keeps your automated newsletters on schedule without requiring manual clicks in the marketing dashboard.

Track campaign performance programmatically

The `get_mailing_statistics` tool pulls real-time open, click, and bounce metrics directly into your OpenAI Agents SDK runtime. Your analysis agent reads these numbers to evaluate performance trends and adjust sending times on the fly. When a campaign finishes, `get_mailing_details` retrieves the structural metadata while `list_unsubscription_events` flags opt-outs to update your internal CRM database. This feedback loop ensures your models make decisions based on fresh engagement data.

Setup guide

Set up Maileon 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 Maileon tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius MCP Server endpoint URL. Pass this server instance inside the `mcp_servers` list when creating your Agent constructor to let the model auto-discover all nine marketing tools.

Yes, calling `create_new_contact` automatically triggers your pre-configured double opt-in flow on the server side. The agent only needs to send the email address and contact fields to start the validation sequence.

The SDK intercepts API rate-limiting headers and respects retry windows. You can configure safety guardrails in your Python code to pause agent execution if the server returns a 429 status code.

Your agent runs `get_mailing_details` to check the current state and configuration of the campaign. If the server shows the campaign is still in a draft state, you must set it to ready before calling the dispatch tool.

Your email marketing contacts and unsubscription logs flow directly through Vinkius's ephemeral V8 sandboxes running the MCP Server without persistent storage. All authentication tokens are handled securely at the proxy level, meaning your agent never exposes raw API credentials to the LLM.

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