How to Use the Amazon Marketing Cloud MCP in Google ADK

Q: Can a Gemini agent built with Google ADK get details about a specific Amazon Marketing Cloud workflow?

Yes, it can. The agent just needs to call the getworkflowdetails tool with the workflow ID. It will get back the full configuration and metadata for that workflow.

Q: Is it possible to list all active executions in Amazon Marketing Cloud using Google ADK?

Absolutely. Your agent calls the listexecutions tool. This returns a list of all current and past executions for a given workflow, including their status and IDs.

Connect your Gemini agents to Amazon Marketing Cloud. Run analytics and pull reports right into your Google Cloud workflow with the ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Marketing Cloud MCP to Google ADK

Create your Vinkius account to connect Amazon Marketing Cloud 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 Amazon Marketing Cloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger AMC Queries from Gemini

Let your Gemini agent run analytics jobs in Amazon Marketing Cloud. It uses the `create_execution` tool to start any SQL query you've defined. This is perfect for kicking off daily reporting or ad-hoc analysis without leaving your GCP environment. Your agent stays in the loop. It can poll `get_execution_status` to know exactly when a job is done. After completion, it uses `get_execution_download_urls` to get the results, ready to be loaded into BigQuery.

Manage AMC Workflows with a Google ADK Agent

This MCP Server gives your agent full control over AMC workflows. Your Gemini agent can build a new analytics pipeline with `create_workflow` or make changes to an existing one using `update_workflow`. It's all managed through the ADK toolset. Your agent can also handle cleanup. It gets a full picture by calling `list_workflows` and `list_executions`. From there, it can programmatically remove old jobs with `delete_workflow` and `delete_execution`, keeping your AMC environment efficient.

Integrate Analytics into Your GCP Stack

This isn't just about running queries; it's about connecting data. Your agent can pull AMC query results and feed them directly into other Google Cloud services. Think of it as a bridge between your advertising analytics and your central data warehouse. Because you're using the Google ADK, your agent benefits from Gemini's large context window. It can reason over complex instructions and past results to decide which AMC workflow to run next, making for a smarter, more autonomous system.

Setup guide

Set up Amazon Marketing Cloud 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 Amazon Marketing Cloud 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="Amazon Marketing Cloud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Amazon Marketing Cloud 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 Amazon Marketing Cloud. 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 Amazon Marketing Cloud 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 Amazon Marketing Cloud MCP in Google ADK

You configure the McpToolset and add it to your LlmAgent. The agent will discover the `create_execution` tool and can call it to start a new query in AMC.

Yes, it can. The agent just needs to call the `get_workflow_details` tool with the workflow ID. It will get back the full configuration and metadata for that workflow.

Absolutely. Your agent calls the `list_executions` tool. This returns a list of all current and past executions for a given workflow, including their status and IDs.

It acts as a secure connector. Your Google ADK agent, running on your infrastructure, makes calls to the server. This lets you trigger AMC actions and pull data without complex, custom integrations.

Your data's privacy is maintained. The server facilitates API calls but doesn't persist your AMC workflow configurations or execution results. When your agent fetches data, it receives a direct, secure download URL from AMC, keeping the data path clean.

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