How to Use the Amazon Ads MCP in Pydantic AI

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

Use the unified MCPToolset class. Pass your Vinkius HTTP endpoint directly into it, then add that toolset to your Agent's toolsets list. Do not use the deprecated MCPServerHTTP method.

Type-safe Amazon Ads agents built with Pydantic AI. Catch bad campaign data at runtime before your agent hallucinates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Ads MCP to Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Amazon Ads MCP Server with Strict Validation

Advertising APIs return messy, nested JSON that easily confuses language models. By running this MCP Server through Pydantic AI, you force every single response into a strict Python model. When your agent calls `list_profiles`, the framework verifies the advertiser IDs match your exact expected schema before the LLM ever sees them. Silent failures cost money in ad tech. If Amazon changes a field name in the `list_sp_campaigns` response, Pydantic AI throws a loud validation error immediately. Your agent stops execution instead of hallucinating a budget number or misinterpreting a metric.

Cross-Model Campaign Management

You are never locked into a single model provider. Pydantic AI is completely model-agnostic, meaning you can use Claude for complex strategy and a cheaper local model for basic data extraction. The agent fires `list_sb_campaigns` to grab your brand assets, regardless of which brain is driving. Digging into targeting specifics works exactly the same way. The agent pulls your active search terms using `list_sp_keywords` and `list_sb_keywords`. Because the framework handles the tool execution, the data always comes back clean and structured for your application logic.

Reliable Performance Reporting

Requesting reports requires exact parameters. Your agent uses `request_sp_report` to ask Amazon for a specific date range and metric set. Pydantic AI ensures the agent formats that initial request perfectly, rejecting invalid date strings before they hit the API. The polling mechanism is equally structured. The agent loops `get_report_status` to check on the file generation. You get a guaranteed, type-checked report ID back every time, making it easy to build automated daily dashboards without worrying about weird edge cases.

Setup guide

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

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

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

Use the unified `MCPToolset` class. Pass your Vinkius HTTP endpoint directly into it, then add that toolset to your Agent's `toolsets` list. Do not use the deprecated `MCPServerHTTP` method.

Runtime validation prevents expensive mistakes. If the API returns unexpected nested structures for `list_sp_ad_groups`, the framework catches it instantly. Your agent never processes corrupted campaign data.

Yes, the agent easily handles multi-account setups. It executes `list_profiles` to fetch the active accounts, and Pydantic ensures the resulting profile IDs are valid strings before passing them to the next tool.

The framework separates the model from the tools. You can run Llama 3 locally to execute `list_sp_keywords` just as easily as you would use GPT-4. The toolset behaves identically.

Security relies on ephemeral execution environments. The moment your agent finishes polling `get_report_status` and downloads your click-through rates, the server instance is wiped. We do not store your advertising API tokens or report payloads.

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