How to Use the Google Ads MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK auto-discover Google Ads tools?

You register the Google Ads MCP Server URL using MCPServerStreamableHttp within your OpenAI Agents SDK Python code. The OpenAI Agents SDK automatically reads the tool schemas, letting your agents call listcampaigns or getperformancereport with zero manual configuration.

Run production-grade Google Ads optimizations using safe agent workflows built with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Google Ads to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded Google Ads budget checks

`get_account_budget` serves as your OpenAI Agents SDK safety rail before making any Google Ads bidding decisions. By reading live Google Ads account caps directly through this MCP Server, your OpenAI Agents SDK system prevents runaway spending before an autonomous agent can commit a bad play. You configure the OpenAI Agents SDK to poll the Google Ads budget endpoint before executing scaling logic. The OpenAI Agents SDK built-in validation checks the live Google Ads balance against your internal hard limits, ensuring no budget gets drained by a rogue execution loop.

Multi-agent campaign audits with OpenAI Agents SDK

`list_campaigns` allows specialized OpenAI Agents SDK workflows to run parallel checks on Google Ads search, display, and shopping setups. Your OpenAI Agents SDK routing agent hands off the Google Ads data to an audit agent, which then pulls targeted ad groups using `list_ad_groups` to find structural issues. This division of labor keeps your OpenAI Agents SDK token usage efficient while running deep Google Ads checks. The OpenAI Agents SDK tracing dashboard traces the exact handoff sequence, showing you which agent queried the live Google Ads campaign list and which one flagged the underperforming assets.

Closed-loop ad performance analysis

`get_performance_report` delivers raw daily Google Ads metrics directly to your OpenAI Agents SDK analysis agent. Instead of manual exports, the OpenAI Agents SDK agent compares these Google Ads performance figures against active keywords pulled via `list_keywords` to find unprofitable targets. The OpenAI Agents SDK matches conversions using `list_conversion_actions` to verify that your Google Ads spend actually drives real business value. Since the OpenAI Agents SDK handles tool schema parsing automatically, your agents instantly map these Google Ads metrics to decision-making prompts without manual schema wiring.

Setup guide

Set up Google Ads MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Google Ads tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Google Ads tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Google Ads tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Google Ads Agent",
            instructions="You have access to Google Ads tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You register the Google Ads MCP Server URL using `MCPServerStreamableHttp` within your OpenAI Agents SDK Python code. The OpenAI Agents SDK automatically reads the tool schemas, letting your agents call `list_campaigns` or `get_performance_report` with zero manual configuration.

Yes, you can write custom validation logic that intercepts OpenAI Agents SDK calls to Google Ads tools like `get_account_budget`. This ensures your agent checks the live Google Ads budget balance before attempting to run any high-volume search or display campaign analyses.

Every Google Ads tool call made by your OpenAI Agents SDK system shows up in your run traces. You will see the exact inputs and outputs for `list_keywords` or `list_ads`, making it easy to debug why an OpenAI Agents SDK agent made a specific Google Ads optimization decision.

The server passes Google Ads API limits directly back to your OpenAI Agents SDK Python runtime. You should configure backoff handlers in your OpenAI Agents SDK loop when calling `list_keywords` across hundreds of Google Ads ad groups to avoid rate limits.

Your Google Ads campaign metrics, keyword lists, and budget limits pass directly through an ephemeral, zero-trust V8 sandbox. This MCP Server never stores your Google Ads credentials or reporting data, keeping your marketing assets isolated within your private OpenAI Agents SDK execution context.

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