How to Use the Apple Search Ads MCP in Pydantic AI

Q: What's the setup process for using Pydantic AI with the Apple Search Ads MCP server?

It's straightforward. After you pip install, you just create an MCPToolset instance with your Vinkius URL. Then you pass that toolset into the toolsets list when you create your Agent. That's it.

Q: What's the difference between MCPToolset and MCPServerHTTP?

MCPToolset is the modern, unified way to do it. MCPServerHTTP is the older, deprecated method. You should always use MCPToolset for any new project.

Get type-safe, validated Apple Search Ads data for your agent. Pydantic AI guarantees your data models match what the API sends.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apple Search Ads MCP to Pydantic AI

Create your Vinkius account to connect Apple Search 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 Apple Search Ads with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Reports That Are Always Correct

When your agent calls `get_campaign_report` or `get_ad_group_report`, the response is instantly parsed into a Pydantic model. If a field is missing, has the wrong data type, or just isn't what you expect, your code raises a `ValidationError`. Right away. That means you can trust the data you're working with. Your agent won't act on bad information or crash because an API field changed unexpectedly. If the data isn't perfect, you'll know exactly why and where it broke.

Use Any LLM You Want

This MCP Server works with any large language model that Pydantic AI supports. You can use `list_campaigns` with an OpenAI model today, then switch to a local model tomorrow without rewriting your tool-handling code. The integration is at the framework level, not the function level. Pydantic AI handles the model-specific prompting and parsing for you. Your code just focuses on the job: getting ad data and deciding what to do with it. It cleanly separates the 'what' from the 'how'.

Build Reliable Ad Automations

Before your agent tries to optimize a campaign, it needs correct data. Tools like `get_campaign` and `list_ad_groups` provide that data in a structure you can depend on, because every response is guaranteed to fit your Pydantic models. This is a huge deal for building automations that don't break. You can write agent logic that assumes the data it gets from this MCP Server is valid, because Pydantic AI acts as a strict bouncer at the door. It's all about making your agent's behavior predictable and correct.

Setup guide

Set up Apple Search 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": {
        "apple-search-ads-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Apple Search 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 Apple Search 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 Apple Search 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 Apple Search Ads MCP in Pydantic AI

The MCP toolset automatically defines Pydantic models for each tool's output. When your agent gets a response from the Apple Search Ads API, Pydantic AI immediately tries to parse it into the corresponding model. If it fails, it raises an error instead of passing bad data to your agent.

Yes. Pydantic AI is model-agnostic. As long as you have a compatible adapter for your local LLM, you can use it to call the Apple Search Ads tools and process the results, all with the same type-safety guarantees.

It's straightforward. After you `pip install`, you just create an `MCPToolset` instance with your Vinkius URL. Then you pass that toolset into the `toolsets` list when you create your `Agent`. That's it.

`MCPToolset` is the modern, unified way to do it. `MCPServerHTTP` is the older, deprecated method. You should always use `MCPToolset` for any new project.

This server only requests your ad performance data and basic account info. Pydantic AI adds a security layer by validating the structure of this data; if the server returned something unexpected or malformed, it would be rejected immediately. The connection is secured by your Vinkius token, and the server itself doesn't persist any of your data.

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