How do I find my Amazon Ads API credentials?

You need to create a 'Login with Amazon' application in the Amazon Developer Console to get your Client ID and Client Secret. Then, you generate a Refresh Token. You also need your AMC Instance ID.

What is an AMC workflow?

A workflow in AMC is a saved SQL query. You can save complex queries as workflows and then execute them repeatedly by triggering a workflow execution.

How do I get the results of my query?

Query executions are asynchronous. First, trigger an execution. Then, check its status. Once the status is COMPLETED, use the `get_execution_download_urls` tool to get a pre-signed S3 link to download the CSV data.

Amazon Marketing Cloud MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Amazon Marketing Cloud
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Amazon Marketing Cloud through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Amazon Marketing Cloud Assistant",
            instructions=(
                "You help users interact with Amazon Marketing Cloud. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Amazon Marketing Cloud"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Amazon Marketing Cloud MCP Server

Connect your Amazon Marketing Cloud (AMC) instance to your AI agent to unlock professional cross-channel advertising analytics. From defining SQL-based workflows to executing ad-hoc queries and retrieving secure download URLs for your reports, your agent handles your AMC data pipelines through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Amazon Marketing Cloud through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Amazon Marketing Cloud, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Workflow Orchestration — List, retrieve, and manage saved SQL workflows to standardize your analytics
Execution Management — Trigger new workflow executions or ad-hoc SQL queries and monitor their processing status
Results Retrieval — Securely fetch S3 download URLs for completed execution outputs directly from chat
Task Oversight — Audit recent execution history and cancel long-running or stalled queries
Data Insights — Quickly organize and trigger complex multi-touch attribution queries without navigating the AWS console

The Amazon Marketing Cloud MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Amazon Marketing Cloud to OpenAI Agents SDK via MCP

Follow these steps to integrate the Amazon Marketing Cloud MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Amazon Marketing Cloud

Why Use OpenAI Agents SDK with the Amazon Marketing Cloud MCP Server

OpenAI Agents SDK provides unique advantages when paired with Amazon Marketing Cloud through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Amazon Marketing Cloud + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Amazon Marketing Cloud MCP Server delivers measurable value.

Automated workflows: build agents that query Amazon Marketing Cloud, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Amazon Marketing Cloud, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Amazon Marketing Cloud tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Amazon Marketing Cloud to resolve tickets, look up records, and update statuses without human intervention

Amazon Marketing Cloud MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Amazon Marketing Cloud to OpenAI Agents SDK via MCP:

create_execution

Execute an AMC query

create_workflow

Create an AMC workflow

delete_execution

Cancel an execution

delete_workflow

Delete an AMC workflow

get_execution_download_urls

Get execution download URLs

get_execution_status

g. PENDING, COMPLETED). Check execution status

get_workflow_details

Get workflow details

list_executions

List workflow executions

list_workflows

List AMC workflows

update_workflow

Update an AMC workflow

Example Prompts for Amazon Marketing Cloud in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Amazon Marketing Cloud immediately.

"List my saved AMC workflows."

"Check the status of execution ID 'exec-12345'."

"Execute workflow 'wkfl-98765' for the last 7 days."

Troubleshooting Amazon Marketing Cloud MCP Server with OpenAI Agents SDK

Common issues when connecting Amazon Marketing Cloud to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Amazon Marketing Cloud + OpenAI Agents SDK FAQ

Common questions about integrating Amazon Marketing Cloud MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.