How to Use the AdButler MCP in Pydantic AI

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

Install pydantic-ai-slimmcp and instantiate MCPToolset with your Vinkius HTTP URL. Pass this toolset directly to your Agent's toolsets list.

Q: How does Pydantic AI prevent my agent from hallucinating AdButler campaign stats?

The framework validates the output of getstats against strict type definitions at runtime. If the model tries to invent or alter statistics, the validation layer blocks the action immediately.

Q: Can I use Pydantic AI to safely manage AdButler advertisers via MCP?

Yes. When you call listadvertisers or getadvertiser, the SDK enforces structured models on the returned profiles. This guarantees your agent always works with clean, verified advertiser data.

Q: Does this setup support both Streamable HTTP and SSE transports?

Yes. The MCPToolset class supports both transport layers, allowing your agent to communicate with the externally running server over your preferred protocol.

Build type-safe ad operations pipelines using Pydantic AI and the AdButler MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdButler MCP to Pydantic AI

Create your Vinkius account to connect AdButler 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 AdButler with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate AdButler Campaign Data with Pydantic AI

The `get_campaign` tool fetches active flight dates, budgets, and targeting criteria directly into your Pydantic AI agent. Pydantic AI enforces strict schemas on these fields, catching API payload changes before they break your application logic. If the server returns unexpected values, the Pydantic AI agent raises a validation error instead of passing bad data to your LLM. This prevents your agent from hallucinating campaign budgets or running ads with incorrect flight dates.

Run Type-Safe Publisher and Zone Audits

The `list_publishers` tool returns structured publisher details that map directly to your local Pydantic AI models. Your agent can safely cross-reference this data with `list_zones` to verify that every zone is mapped to an active publisher. Because this MCP Server uses standard HTTP transport, you can register the `MCPToolset` with your Pydantic AI agent in two lines of code. The framework validates every zone configuration returned, ensuring your layout logic stays intact.

Track Ad Performance Without Silent Errors

The `get_stats` tool provides raw impression and click data that your Pydantic AI agent parses into strictly typed performance reports. This ensures that numeric values like click-through rates are never interpreted as strings by your model. By calling `list_banners` alongside performance metrics, your Pydantic AI agent matches specific creatives to their actual delivery numbers. If a banner record is missing required fields, the runtime validation catches it instantly.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and instantiate `MCPToolset` with your Vinkius HTTP URL. Pass this toolset directly to your Agent's `toolsets` list.

The framework validates the output of `get_stats` against strict type definitions at runtime. If the model tries to invent or alter statistics, the validation layer blocks the action immediately.

Yes. When you call `list_advertisers` or `get_advertiser`, the SDK enforces structured models on the returned profiles. This guarantees your agent always works with clean, verified advertiser data.

Yes. The `MCPToolset` class supports both transport layers, allowing your agent to communicate with the externally running server over your preferred protocol.

Authentication tokens are managed securely by Vinkius and never exposed to the LLM. Your AdButler ad serving statistics and advertiser profiles are processed in memory within an ephemeral sandbox, then discarded immediately after your Pydantic AI agent runs.

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