How to Use the Emma MCP in Google ADK

Q: How do I configure Emma with the Google ADK?

Use the McpToolset class with StreamableHttpServerParameters pointing to your Vinkius URL. Pass this toolset directly to your LlmAgent array. You can restrict which endpoints the agent sees using the optional toolnames filter.

Q: Are my custom member fields secure during these queries?

Endpoints like listfields and getmember transmit sensitive schema details and subscriber PII. This MCP Server operates inside an isolated sandbox that spins up solely for your request. Once the HTTP response fires, the environment evaporates entirely.

Give your Gemini models direct access to Emma marketing data using the Google ADK MCP Server setup.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Emma MCP to Google ADK

Create your Vinkius account to connect Emma 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 Emma with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze campaigns with Google ADK

The Emma MCP Server feeds campaign metrics straight into your Gemini context window using `list_mailings` and `get_mailing_stats`. Your agent runs the first tool to grab the historical send log, then iterates through the stats endpoint to pull the performance numbers. It handles massive datasets easily thanks to Gemini's long-context capabilities. Enterprise setups usually want this data in BigQuery. The agent pulls the open and click rates, structures the output, and pushes it to your data warehouse. You get automated reporting without writing custom ETL pipelines.

Query subscriber details

Finding specific users happens through the `get_member` and `list_members` tools. Your agent searches the active database to see who received what. If you need to understand the custom data structure, `list_fields` exposes the exact schema Emma uses for your accounts. Here is the thing about context. Because Google ADK supports deep reasoning, the agent cross-references these member profiles with your internal Vertex AI models to predict churn or engagement.

Control list infrastructure

You dictate list architecture using `create_group` and `list_groups`. The agent checks existing buckets and builds new ones for upcoming product launches. It operates entirely hands-off. Maintenance is just as easy. The agent can trigger `delete_group` to drop empty or outdated segments, while keeping the actual subscribers intact. It also checks `list_automations` and `list_webhooks` to confirm your external triggers remain active.

Setup guide

Set up Emma 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 Emma 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="Emma_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Emma 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 Emma. 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 Emma 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 Emma MCP in Google ADK

Use the `McpToolset` class with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass this toolset directly to your `LlmAgent` array. You can restrict which endpoints the agent sees using the optional `tool_names` filter.

Absolutely. Your agent fetches subscriber metrics via the MCP Server and writes them to your Google Cloud infrastructure. This makes blending email marketing stats with your sales data incredibly straightforward.

The members survive. That tool only destroys the folder structure, not the people inside it. Your total subscriber count remains untouched.

Gemini's massive 1M+ token context window eats large JSON payloads for breakfast. When you call `list_members`, the model holds the entire list in memory to perform complex reasoning or segmentation tasks.

Endpoints like `list_fields` and `get_member` transmit sensitive schema details and subscriber PII. This MCP Server operates inside an isolated sandbox that spins up solely for your request. Once the HTTP response fires, the environment evaporates entirely.

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