How to Use the Adtraction MCP in Pydantic AI

Q: How do I configure Adtraction inside Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Use the unified MCP toolset class initialized with your Vinkius HTTP endpoint, and pass it to your Agent's toolsets parameter.

Build type-safe affiliate agents with Pydantic AI and Adtraction.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adtraction MCP to Pydantic AI

Create your Vinkius account to connect Adtraction 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 Adtraction with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Affiliate Auditing with Pydantic AI

Never worry about silent API changes breaking your affiliate tracking scripts again. Pydantic AI validates every single payload returned from the network at runtime. When your agent calls `list_transactions`, the framework ensures the transaction amounts and IDs match your expected Python types exactly. If the network API returns unexpected null values or modified fields, the framework raises a validation error immediately. This strict validation prevents corrupt transactional data from contaminating your internal databases or financial reports.

Validate Program Details with this MCP Server

Fetching affiliate program terms requires absolute precision. Your agent uses this MCP Server to retrieve commission rates, rules, and tracking links via `get_program_details`. Pydantic AI parses this data against strict models, ensuring your agent never acts on malformed or incomplete program information. You can also search the network by calling `list_programs` to find new campaigns. The agent filters these opportunities based on type-safe parameters, making it impossible for the model to hallucinate non-existent affiliate offers.

Audit Traffic Channels Without Runtime Surprises

Keep your media channels compliant by monitoring them programmatically. The agent queries your approved traffic sources via `list_channels` and tracks performance metrics using `get_stats_by_program`. Every statistic is parsed into a clean Pydantic model before your agent processes it. This model-agnostic approach means you can swap your underlying LLM from Anthropic to OpenAI without changing your validation logic. Your Adtraction data remains structured and safe, regardless of which model is reasoning over it.

Setup guide

Set up Adtraction 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": {
        "adtraction-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Run pip install "pydantic-ai-slim[mcp]". Use the unified MCP toolset class initialized with your Vinkius HTTP endpoint, and pass it to your Agent's toolsets parameter.

The framework will raise a validation error instantly. Instead of letting your agent hallucinate or process bad data, the run fails loudly so you can fix schema mismatches immediately.

Yes. Pydantic AI supports both Streamable HTTP and SSE transports. You can connect to your externally running Vinkius server using either protocol.

Yes. The framework handles MCP tool discovery and schema caching during initialization, ensuring your agent doesn't waste network requests fetching schemas repeatedly.

Your sensitive channel lists and transaction histories are never stored by the framework. All requests pass through Vinkius's secure, zero-trust V8 sandboxes over HTTPS, keeping your affiliate revenue data completely private.

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