How to Use the Google Ads MCP in Google ADK

Q: How do I initialize the Google Ads MCP Server inside a Google ADK agent?

Install google-adk and define your McpToolset using your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent constructor to expose tools like listcampaigns to your Gemini model.

Q: How does Gemini's long context window benefit my Google Ads workflows?

It allows the agent to ingest massive outputs from getcampaignreport without truncation. The agent can compare performance across hundreds of ad groups simultaneously, which standard models can't handle.

Analyze millions of Google Ads data points in BigQuery using Gemini and the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Ads MCP to Google ADK

Create your Vinkius account to connect Google Ads 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 Google Ads with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise Google Ads Analysis with Google ADK

Gemini models thrive on massive context, making them perfect for parsing years of marketing data. By linking this MCP Server to your Google ADK setup, your agent can pull massive reports without hitting token limits. It runs `get_campaign_report` to ingest raw performance data directly. You can combine this live ad data with your internal warehouse. The agent queries your customer lifetime value metrics in BigQuery, correlates them with `get_ad_performance` data, and identifies which ad groups actually drive real profit.

Direct Vertex AI Integration for Keyword Discovery

Stop manual keyword exports. Your Google ADK agent can now query your live account setup using this MCP Server. It runs `list_ad_groups` to map your current structure, then uses Google Cloud's machine learning tools to predict search trend shifts. Once the model identifies gaps, it calls `search_keywords` to validate search volume and competition. This gives you a closed-loop system where your enterprise data pipeline informs your search marketing strategy in real time.

Multi-Account Oversight at Scale

Managing dozens of client accounts requires serious organization. This toolset lets your Gemini agent scan your entire organizational hierarchy in seconds. It starts by calling `list_accessible_customers` to map out every connected account. From there, the agent runs `get_account_summary` across your portfolio to flag underperforming budgets. Because the Google ADK handles long-context reasoning, the agent can analyze all client summaries simultaneously without losing track of details.

Setup guide

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

Install `google-adk` and define your `McpToolset` using your Vinkius HTTP endpoint. Pass this toolset into your `LlmAgent` constructor to expose tools like `list_campaigns` to your Gemini model.

Yes, easily. Your agent can query your historical sales data in BigQuery and use `get_keyword_performance` to compare offline conversions against active search ad metrics in the same run.

Yes, it does. You can connect your Google Ads agent using either transport method, though Vinkius-managed MCP endpoints are recommended for production cloud deployments.

It allows the agent to ingest massive outputs from `get_campaign_report` without truncation. The agent can compare performance across hundreds of ad groups simultaneously, which standard models can't handle.

Yes. Your Google Ads account summaries and performance metrics are processed inside zero-trust, ephemeral V8 sandboxes. No credentials or raw marketing data are stored on Vinkius servers or used for model training.

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