How to Use the Amazon Marketing Cloud MCP in Pydantic AI

Q: How does Pydantic AI handle creating a new workflow in Amazon Marketing Cloud?

Your agent calls the createworkflow tool. Pydantic AI ensures the arguments you pass match the required schema. The response is then validated, so you get a predictable workflow object back or a clear error.

Q: Can I use Pydantic AI to check the status of multiple Amazon Marketing Cloud jobs?

Yes. You can have your agent call listexecutions for a specific workflow. Pydantic AI will validate the entire list, ensuring every execution object in the response is correctly formed before your code touches it.

Bring type-safe control to Amazon Marketing Cloud. Your Pydantic AI agent gets validated, predictable responses for every analytics call.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Marketing Cloud MCP to Pydantic AI

Create your Vinkius account to connect Amazon Marketing Cloud 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 Marketing Cloud with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute AMC Queries with Confidence

Kick off AMC analytics jobs and trust the response. Your agent calls `create_execution` and gets back a Pydantic model. If the API returns anything unexpected, Pydantic AI throws a validation error immediately. No silent failures. You can build a reliable monitoring loop. The agent periodically calls `get_execution_status`. The response is a validated enum, so you know the status is one of the expected values—`PENDING`, `COMPLETED`, etc.—and not some random string.

Build Resilient AMC Workflow Management

This MCP Server lets your agent manage AMC workflows with guaranteed schema correctness. When you call `create_workflow` or `update_workflow`, you're working with structured Pydantic objects, not loose dictionaries. It makes your agent code cleaner and more robust. The same principle applies to reading data. Calls to `list_workflows` or `get_workflow_details` return validated models. Your agent won't crash because of a missing key or an incorrect data type in the API response.

Your Pydantic AI Agent Is Always in Sync

Forget about parsing messy JSON. When your agent needs to fetch results using `get_execution_download_urls`, the response is a clean, typed list of URL objects. This eliminates a common source of bugs in data-handling code. This focus on correctness extends to cleanup, too. Tools like `delete_workflow` and `delete_execution` provide clear, validated confirmation responses. Your Pydantic AI agent always has a precise understanding of the state of your Amazon Marketing Cloud resources.

Setup guide

Set up Amazon Marketing Cloud 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-marketing-cloud-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Data integrity. Every response from the Amazon Marketing Cloud MCP server is parsed and validated against a Pydantic model before your Pydantic AI agent can use it. This prevents errors from unexpected API changes or malformed data.

Your agent calls the `create_workflow` tool. Pydantic AI ensures the arguments you pass match the required schema. The response is then validated, so you get a predictable workflow object back or a clear error.

Yes. You can have your agent call `list_executions` for a specific workflow. Pydantic AI will validate the entire list, ensuring every execution object in the response is correctly formed before your code touches it.

It does. Pydantic AI is model-agnostic. You can use it with OpenAI, Anthropic, Gemini, or a self-hosted model, and the type-safe guarantees for this server will work the same way.

The server only handles the API transaction. It passes your requests to AMC and returns AMC's response. Your sensitive data, like workflow details and execution results, is not stored or logged by Vinkius. Pydantic AI simply validates the structure of this data in-memory on your agent's side.

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