How to Use the MJML (Email Markup) MCP in OpenAI Agents SDK

Q: How do I configure MJML (Email Markup) in OpenAI Agents SDK?

Install the SDK using pip install openai-agents and define the MCP Server with MCPServerStreamableHttp. Pass this instance directly into your Agent constructor within an async with block. The agent auto-discovers the rendermjml tool, making it ready for production immediately.

Q: How does the agent handle malformed MJML syntax?

The rendermjml tool returns a detailed error message describing the line and character where the XML parsing failed. The agent reads this error directly and can attempt to fix the syntax before retrying the compilation.

Q: Is my raw email markup secure when using this server?

The Vinkius sandbox executes the rendermjml parser in a secure, ephemeral V8 isolate using our managed MCP gateway. Your raw MJML XML strings are processed in memory and destroyed immediately after the HTML is returned, leaving no persistent footprint on our servers.

Build production-ready email agents with the OpenAI Agents SDK and this MJML MCP Server to compile raw markup into responsive HTML.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MJML (Email Markup) MCP to OpenAI Agents SDK

Create your Vinkius account to connect MJML (Email Markup) 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 MJML (Email Markup) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Compile raw MJML markup directly inside OpenAI Agents SDK

The `render_mjml` tool converts raw MJML XML or JSON strings into responsive HTML layout code. Your OpenAI agent invokes this tool during execution, receiving fully rendered email structures that look identical across Outlook and Gmail without you writing a single table tag. You register this tool by passing the MCP Server endpoint to the `MCPServerStreamableHttp` constructor. By setting `cacheToolsList=True`, the agent avoids redundant network requests, keeping your transactional email pipelines running fast.

Protect mail delivery with native SDK guardrails

Running the `render_mjml` tool inside this SDK means you can apply strict pre-execution guardrails before sending HTML to your ESP. The agent validates the generated payload against your delivery rules, preventing broken layouts or missing dynamic tags from ever hitting a user's inbox. If the output exceeds Gmail's strict 102KB clipping limit, the SDK intercepts the execution. This setup ensures your marketing agents never dispatch bloated templates, protecting your domain reputation automatically.

Trace email rendering across agent handoffs

This MCP Server integrates with the OpenAI developer dashboard, giving you complete visibility into how your agents format communications. When a specialized copywriter agent hands off a draft to a layout agent, the exact inputs and outputs of the `render_mjml` tool are logged in real-time. You see the raw XML payload go in and the processed HTML come out. This makes debugging template errors fast, letting you pinpoint syntax mistakes without digging through terminal logs.

Setup guide

Set up MJML (Email Markup) 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 MJML (Email Markup) tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK using `pip install openai-agents` and define the MCP Server with `MCPServerStreamableHttp`. Pass this instance directly into your `Agent` constructor within an `async with` block. The agent auto-discovers the `render_mjml` tool, making it ready for production immediately.

Yes. You can share the toolset across multiple specialized agents. A drafting agent can write the copy, then pass the context to a design agent that runs the `render_mjml` tool to generate the final HTML.

The latency is minimal, averaging under 40ms per render. To keep execution times low, set `cacheToolsList=True` in your server parameters so the SDK does not fetch the tool definition on every loop.

The `render_mjml` tool returns a detailed error message describing the line and character where the XML parsing failed. The agent reads this error directly and can attempt to fix the syntax before retrying the compilation.

The Vinkius sandbox executes the `render_mjml` parser in a secure, ephemeral V8 isolate using our managed MCP gateway. Your raw MJML XML strings are processed in memory and destroyed immediately after the HTML is returned, leaving no persistent footprint on our servers.

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