How to Use the Amazon DSP MCP in Pydantic AI

Q: How do I initialize the Amazon DSP toolset in Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp" and instantiate MCPToolset with your Vinkius HTTP URL. Pass this toolset directly into the Agent constructor's toolsets argument.

Build type-safe Amazon DSP integrations using Pydantic AI and this MCP Server to catch API errors before they break your pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon DSP MCP to Pydantic AI

Create your Vinkius account to connect Amazon DSP 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 Amazon DSP with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Runtime Validation for Amazon DSP Campaigns

Your agent uses `get_campaign_details` to fetch specific configuration data, validating every single field against strict Pydantic models at runtime. If the Amazon DSP API returns unexpected null values or modified data types, Pydantic AI halts execution immediately. This strictness prevents corrupted campaign data from polluting your downstream systems. Instead of silently failing or hallucinating missing fields, your agent raises a clear validation error you can debug instantly.

Type-Safe Reporting with this MCP Server

This MCP Server lets your agent trigger `request_report` and monitor its progress via `get_report_status` with absolute type safety. Pydantic AI guarantees that the report status strings and IDs match your schema exactly before processing continues. By enforcing these strict types, you ensure that raw performance metrics are parsed correctly every single time. It makes your automated reporting pipelines incredibly stable, even when Amazon updates its DSP API payload structures.

Audience and Creative Structure Validation

The agent queries `list_audiences` to pull targeting segments, mapping the response directly to your custom Pydantic schemas. It does the same with `list_creatives`, ensuring that image dimensions, asset URLs, and creative IDs are fully validated. Since Pydantic AI is model-agnostic, you can run these validated tools using OpenAI, Anthropic, or local models. The validation happens at the framework level, giving you consistent data integrity regardless of which LLM powers your agent.

Setup guide

Set up Amazon DSP 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": {
        "amazon-dsp-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your Vinkius HTTP URL. Pass this toolset directly into the `Agent` constructor's `toolsets` argument.

Pydantic AI will raise a validation error immediately, preventing the agent from acting on malformed data. This is crucial when calling `list_ad_groups`, as it protects your pipeline from silent field corruption.

Yes, the framework is model-agnostic, allowing you to run tools like `list_campaigns` using local LLMs or commercial APIs. The runtime validation ensures that even less capable models adhere strictly to your DSP data schemas.

Yes, you connect to the external Amazon DSP server using the unified toolset over streamable HTTP or SSE transports. This keeps your agent code clean and decoupled from the running MCP Server instance.

The framework never sees your raw API keys because Vinkius manages all MCP authentication at the proxy layer. Your validated audience lists, creative assets, and campaign details are processed within ephemeral, zero-trust V8 isolates.

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