How to Use the AdRoll MCP in Pydantic AI

Q: How do I set up the AdRoll MCP server with Pydantic AI?

After installing pydantic-ai-slimmcp, you create an MCPToolset instance, passing it your Vinkius server URL. Then you include that toolset in the toolsets list when you initialize your Agent. It's a single line to add the entire AdRoll toolset.

Q: What happens if the AdRoll API changes?

Your Pydantic AI agent will fail loudly with a ValidationError on the first call that returns an unexpected structure. This is a feature, not a bug. It prevents your system from processing corrupted or changed data formats, forcing you to update your models deliberately.

Get type-safe, validated AdRoll data in your Python agent. Pydantic AI ensures the data you get is the data you expect.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdRoll MCP to Pydantic AI

Create your Vinkius account to connect AdRoll 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 AdRoll with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guaranteed Data Structures from AdRoll

The `get_report` tool pulls performance data, and Pydantic AI forces it to match your predefined Pydantic model. If AdRoll ever adds a new field or changes a data type unexpectedly, your code will raise a `ValidationError` instead of silently failing or passing bad data downstream. This applies to every tool. Whether you're using `list_campaigns` to get a list of campaigns or `get_campaign` for a single record, Pydantic AI acts as a strict gatekeeper. You write your agent logic with the confidence that the data shapes are always correct.

Build Correctness-First Marketing Agents

This MCP Server gives your agent the tools to query your AdRoll account, like `list_advertisables` and `list_adgroups`. The real power comes from defining the expected output of these tools as Pydantic models in your own code. Your agent isn't just getting a JSON blob; it's getting an instantiated, validated Python object. This makes your agent's logic simpler and far less prone to errors caused by unexpected API responses. Correctness is the default.

A Model-Agnostic AdRoll MCP Server

Pydantic AI doesn't care if you're using OpenAI, Anthropic, or a local model. You can point any compatible LLM at the AdRoll toolset, and the validation layer works the same way. Use `list_segments` and `list_ads` to gather information for your agent. No matter which model generates the request to call these tools, the response from the MCP Server will be rigorously checked against your Pydantic models before your agent can use it.

Setup guide

Set up AdRoll 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": {
        "adroll-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent AdRoll 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 AdRoll. 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 AdRoll 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 AdRoll MCP in Pydantic AI

Pydantic AI inspects the tool's schema, and when the AdRoll server sends back data from a tool like `get_report`, it attempts to parse that JSON into a Pydantic model. If there's any mismatch—a wrong data type, a missing field—it raises an exception immediately.

After installing `pydantic-ai-slim[mcp]`, you create an `MCPToolset` instance, passing it your Vinkius server URL. Then you include that toolset in the `toolsets` list when you initialize your `Agent`. It's a single line to add the entire AdRoll toolset.

Your Pydantic AI agent will fail loudly with a `ValidationError` on the first call that returns an unexpected structure. This is a feature, not a bug. It prevents your system from processing corrupted or changed data formats, forcing you to update your models deliberately.

Yes. Pydantic AI is model-agnostic. As long as your local model can use tools, you can connect it to the AdRoll toolset and get the same type-safe validation you'd get with a commercial model provider.

All requests for your AdRoll campaign and performance data go through a dedicated, sandboxed instance on Vinkius. Access is controlled by a unique token, and the runtime environment for each tool call is temporary. We don't persist your AdRoll 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