How to Use the MJML (Email Markup) MCP in Google ADK

Q: How do I connect MJML (Email Markup) to Google ADK?

Install the package with pip install google-adk and create an McpToolset pointing to the MCP Server's HTTP endpoint. Pass this toolset into your LlmAgent constructor to expose the rendering capability to your Gemini model.

Q: Can I restrict which tools from MJML (Email Markup) are visible in Google ADK?

Yes. You can use the optional toolnames filter in your McpToolset configuration to expose only the rendermjml tool. This keeps your agent's action space clean and prevents unnecessary tool calls.

Q: How does the agent handle email rendering errors?

If the input markup is invalid, the rendermjml tool returns a structured error payload. Your agent can read the specific validation failures and adjust its output before attempting another render.

Generate responsive templates from BigQuery using the Google ADK and this MJML MCP Server.

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 Google ADK

Create your Vinkius account to connect MJML (Email Markup) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render responsive HTML directly within the Google ADK

The `render_mjml` tool translates your email layouts from XML markup to responsive HTML templates on the fly. This tool allows your Gemini-powered agents to generate production-ready email bodies without manually writing nested tables or inline CSS. You initialize this MCP toolset by adding `McpToolset` to your configuration. The agent calls the transpiler whenever your pipeline requires an email update, ensuring consistent layouts across mobile and desktop clients.

Build dynamic email campaigns from BigQuery data

This MCP Server connects your enterprise data pipeline to responsive email generation. Your agent pulls customer segments from BigQuery, feeds those details into an MJML template, and executes the `render_mjml` tool to output personalized HTML. By running this directly inside Google Cloud infrastructure, you eliminate external API hops. The agent manages the entire flow from SQL query to rendered HTML in a single execution thread.

Process complex layouts with long-context reasoning

This MCP Server works with Gemini's million-token context window to analyze entire directories of MJML templates at once. The agent compares previous layouts, suggests optimizations, and runs `render_mjml` to test the changes instantly. This approach ensures that even highly complex, multi-section newsletter templates are parsed and updated without running out of memory. You get fast, iterative updates to your email assets in a secure environment.

Setup guide

Set up MJML (Email Markup) MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with MJML (Email Markup) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="MJML (Email Markup)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to MJML (Email Markup) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package with `pip install google-adk` and create an `McpToolset` pointing to the MCP Server's HTTP endpoint. Pass this toolset into your `LlmAgent` constructor to expose the rendering capability to your Gemini model.

Yes. You can use the optional `tool_names` filter in your `McpToolset` configuration to expose only the `render_mjml` tool. This keeps your agent's action space clean and prevents unnecessary tool calls.

No, the server runs in a managed, secure cloud environment hosted by Vinkius. Your Google ADK agent connects to the server via streamable HTTP, sending markup and receiving the compiled HTML payload securely.

If the input markup is invalid, the `render_mjml` tool returns a structured error payload. Your agent can read the specific validation failures and adjust its output before attempting another render.

All MJML XML strings sent to the server are processed inside an isolated, zero-trust container. The data is processed in-memory, and the container is discarded immediately after execution, ensuring your email copy and customer templates 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