How to Use the Google Ads MCP in AutoGen

Q: How do AutoGen agents access this Google Ads MCP Server?

You register the Google Ads server using the mcpservertools function with your Vinkius HTTP endpoint. The AutoGen McpToolAdapter automatically translates tools like listadgroups into schemas that your AutoGen AssistantAgent can understand.

Let your AutoGen agents debate Google Ads performance and coordinate budget changes.

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 AutoGen

Create your Vinkius account to connect Google Ads to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate Google Ads performance

The `get_ad_performance` tool feeds live Google Ads creative metrics directly into your AutoGen multi-agent conversation. An AutoGen performance analyst agent can review these Google Ads metrics and argue for pausing low-performing creatives, while a creative agent defends the copy. This structured AutoGen debate ensures you don't make rash decisions based on short-term Google Ads statistical noise. You configure these AutoGen agents to use this Google Ads MCP Server to settle disputes with raw data. By requiring AutoGen consensus before any Google Ads strategy shift, you prevent individual agents from making uncoordinated changes. The AutoGen conversation continues until both agents agree on the best Google Ads optimization path.

Coordinate budget shifts via consensus

The `list_campaigns` tool provides a complete list of active campaigns to your AutoGen budget committee. One AutoGen agent analyzes high-performing campaigns using `get_campaign_report`, while another checks overall Google Ads account limits. They negotiate how to distribute remaining Google Ads funds to maximize conversion volume across your AutoGen framework. This AutoGen multi-agent setup ensures that Google Ads budget reallocations don't happen in a vacuum. The AutoGen agents cross-reference Google Ads campaign details with historical performance to avoid over-allocating to volatile keywords. You get a balanced, logical Google Ads budget strategy driven by automated AutoGen deliberation.

Validate keyword strategies with an MCP Server

The `get_keyword_performance` tool gives your AutoGen agents the exact metrics they need to evaluate Google Ads search term efficiency. A search specialist AutoGen agent proposes new keyword targets, while a finance agent checks the Google Ads cost per conversion. This AutoGen negotiation keeps your keyword expansion strategy aligned with your actual Google Ads acquisition costs. By using the AutoGen McpToolAdapter, the framework automatically maps these Google Ads tool schemas to your agents' capabilities. The AutoGen agents query `search_keywords` to find new Google Ads opportunities and debate their relevance before recommending them. It turns Google Ads keyword research into a collaborative, data-validated process inside your AutoGen workflow.

Setup guide

Set up Google Ads MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Google Ads tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Google Ads_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Google Ads data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Google Ads_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Google Ads data")
    print(result.messages[-1].content)

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 AutoGen

You register the Google Ads server using the mcp_server_tools function with your Vinkius HTTP endpoint. The AutoGen McpToolAdapter automatically translates tools like `list_ad_groups` into schemas that your AutoGen AssistantAgent can understand.

Yes, you can pass the Google Ads tool list to multiple agents in your AutoGen group chat. The performance agent can call `get_campaign_report` while the budget agent can call `list_budgets` to coordinate their Google Ads analysis.

You create two distinct AutoGen AssistantAgent instances, giving one access to `get_keyword_performance` and the other to historical Google Ads reports. They discuss the Google Ads data in an AutoGen RoundRobinGroupChat to reach a consensus on bidding strategy.

Yes, this Google Ads MCP Server can connect to AutoGen via both transports. For managed Vinkius deployments, you will use the Streamable HTTP transport with your secure endpoint token inside your AutoGen setup.

Your Google Ads keyword metrics and campaign settings are processed via this Google Ads MCP Server inside an ephemeral, zero-trust sandbox. Vinkius secures the transport layer and never stores or exposes your Google Ads account data to external networks or other AutoGen workflows.

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