How to Use the Google Ads MCP in Pydantic AI

Q: How does Pydantic AI prevent silent failures with Google Ads?

The framework validates every response from getcampaign and listads against strict Pydantic AI models. If the Google Ads schema doesn't match, Pydantic AI raises a validation error instead of letting your agent run on bad data.

Q: How do I initialize the Google Ads MCP Server in Pydantic AI?

You use the unified Pydantic AI MCPToolset constructor with your Vinkius HTTP endpoint. This exposes all eight Google Ads tools, including listcampaigns and listadgroups, directly to your agent.

Keep your Google Ads agent workflows 100% type-safe and validate campaign data at runtime with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Google Ads to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict budget validation with Pydantic AI

`get_account_budget` provides real-time Google Ads financial boundaries that are parsed directly into strict Pydantic AI types. Pydantic AI guarantees that your agent never acts on corrupted or missing Google Ads budget data by validating every field at runtime. If the Google Ads API returns an unexpected null value or an altered data format, your Pydantic AI application raises a validation error immediately. This loud failure protects your Google Ads account from making automated bids based on faulty calculations in your Pydantic AI system.

Type-safe keyword and ad group mapping

`list_keywords` retrieves your Google Ads search terms and match types directly into structured Pydantic AI models. Your Pydantic AI agent uses these typed objects to safely filter out underperforming Google Ads keywords without risking runtime type exceptions. Mapping these Google Ads keywords to parent structures retrieved via `list_ad_groups` keeps your Pydantic AI application highly organized. Because every Google Ads field is strictly typed, your Pydantic AI code remains clean, maintainable, and free from silent data corruption issues.

Verified conversion tracking via MCP Server schemas

`list_conversion_actions` pulls your active Google Ads conversion definitions into validated Pydantic AI schemas. Pydantic AI ensures that your analysis agent only optimizes Google Ads campaigns against real, verified conversion goals. Cross-referencing these actions with Google Ads performance data from `get_performance_report` allows the Pydantic AI agent to maintain complete accuracy. Any mismatch in Google Ads metric formats is caught instantly, keeping your automated Pydantic AI bidding loops completely accurate.

Setup guide

Set up Google Ads MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "google-ads-1-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Google Ads tools.",
)

result = await agent.run("List recent Google Ads transactions")
print(result.output)

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 Pydantic AI

The framework validates every response from `get_campaign` and `list_ads` against strict Pydantic AI models. If the Google Ads schema doesn't match, Pydantic AI raises a validation error instead of letting your agent run on bad data.

Yes, Pydantic AI is completely model-agnostic. You can use Anthropic, OpenAI, or Gemini models to analyze Google Ads performance reports pulled via `get_performance_report`.

You use the unified Pydantic AI `MCPToolset` constructor with your Vinkius HTTP endpoint. This exposes all eight Google Ads tools, including `list_campaigns` and `list_ad_groups`, directly to your agent.

The framework supports streamable HTTP and SSE transports for Google Ads data. This allows your Pydantic AI agent to fetch live metrics via `get_performance_report` without blocking your main application thread.

Your Google Ads conversion schemas and action names are processed inside ephemeral, zero-trust V8 isolates. The server never stores your Google Ads tokens, ensuring your conversion tracking setup remains entirely private to your Pydantic AI runtime.

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