How to Use the Maildroppa MCP in OpenAI Agents SDK

Q: What's the best way to set up Maildroppa with the OpenAI Agents SDK for performance?

Use the MCPServerStreamableHttp class and set cacheToolsList=True when you instantiate your agent. This stops the SDK from re-fetching the tool list on every single run.

Q: How do I handle multiple subscribers with Maildroppa and the OpenAI Agents SDK?

You can have your agent call listsubscribers to get all your users, then loop through them to perform batch operations like addtagtosubscriber. This works well for building specialized agents that handle list cleanup.

Build production-ready email marketing agents with the safety and tracing of 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 Maildroppa MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Subscribers Safely

Your agent can now manage your Maildroppa list directly through this MCP Server. Use it to `create_subscriber` when someone signs up, or `update_subscriber` if they change their details. The SDK's built-in guardrails will validate every action before it runs, so you don't have to worry about an agent messing up your list. You can also ask your agent to find specific users with `get_subscriber_details` and then apply a new tag using `add_tag_to_subscriber`. All these actions are logged in your OpenAI dashboard, giving you a full trace of what your agent did and why.

Automate List Segmentation

This setup exposes all the tools needed for smart list management. Your agent can `list_tags` and `list_segments` to understand your current configuration. Then, you can instruct it to build a new audience by calling `create_segment` based on your own criteria. It gets better when you combine tools. Have the agent `list_subscribers` with a specific tag, then use that output to create a new, highly targeted segment. This is perfect for building hand-offs between specialized agents—one for analysis, another for execution.

Connect Forms and Fields

Give your agent full context on how you capture leads. It can `list_sign_up_forms` to see which entry points you have and `list_custom_fields` to understand what data you collect beyond just an email address. When you need to update a user's profile, the agent can use `update_subscriber_field` to change a single piece of information, like their city or a custom preference. Set `cacheToolsList=True` in your setup, and the agent will discover these MCP tools instantly on subsequent runs.

Setup guide

Set up Maildroppa 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 Maildroppa tools at runtime.
3

Create your Agent

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

Run the agent

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

The SDK auto-discovers the 12 Maildroppa tools from the server. You can then instruct your agent in plain language to perform actions like `create_subscriber` or `add_tag_to_subscriber`, and the agent executes them.

Yes. The SDK has built-in guardrails that can require confirmation for sensitive actions. Plus, this Maildroppa MCP server doesn't include a delete tool, which adds another layer of safety.

Use the `MCPServerStreamableHttp` class and set `cacheToolsList=True` when you instantiate your agent. This stops the SDK from re-fetching the tool list on every single run.

You can have your agent call `list_subscribers` to get all your users, then loop through them to perform batch operations like `add_tag_to_subscriber`. This works well for building specialized agents that handle list cleanup.

The server only accesses the Maildroppa data needed to run a specific tool, like subscriber emails, names, and tags. Your Vinkius endpoint is sandboxed and ephemeral, so data is only processed in memory for that request.

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