How to Use the Amazon Marketing Cloud MCP in Mastra AI

Q: Can I require human approval before Mastra AI deletes an Amazon Marketing Cloud workflow?

Yes, you can configure Mastra's requireToolApproval on the deleteworkflow tool. The agent pauses execution and waits for a manual confirmation before removing any SQL configurations from AMC.

Q: How do I register the Amazon Marketing Cloud MCP Server tools in Mastra AI?

You initialize the server via the MCPClient constructor, then spread the tools from listTools() into your Mastra Agent's tool array. The framework automatically registers the SQL and workflow management capabilities.

Q: Does this setup support scheduling recurring SQL executions?

Yes, you can use Mastra's workflow engine to trigger createexecution on a cron schedule. The agent will run the query, monitor its status, and send the final download URLs to your database.

Build resilient, self-healing Amazon Marketing Cloud workflows in Mastra AI with automatic retries and conditional branching.

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 Mastra AI

Create your Vinkius account to connect Amazon Marketing Cloud to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient AMC Query Execution Pipelines

This MCP Server provides `create_execution` and `get_execution_status` to let Mastra AI agents run complex SQL queries with built-in retry logic. If Amazon's API returns a transient rate limit, the Mastra workflow engine backs off and retries automatically. You define the execution steps inside a Mastra agent, which polls the status until completion. If a query fails, the agent can inspect the error, adjust the SQL parameters, and trigger a new execution without crashing your production service.

Conditional AMC Workflow Upgrades in Mastra AI

You can automate marketing campaign adjustments by chaining `list_workflows` and `update_workflow` inside Mastra AI's conditional routing engine via this MCP Server. The agent checks existing SQL structures and only pushes updates if specific performance thresholds are met. This setup lets you build autonomous optimization loops. If a workflow fails validation, Mastra halts the pipeline and triggers a Slack notification for manual approval before any AMC changes go live.

Automated AMC File Cleanup

Cleaning up obsolete marketing data is easy when you pair `list_executions` with `delete_workflow` inside a Mastra AI scheduled task. The agent scans your active AMC workflows and flags unused configurations for removal. By automating this maintenance, you keep your AWS clean room clean and organized. Mastra handles the entire execution list, checking each item's age before calling the delete tool.

Setup guide

Set up Amazon Marketing Cloud MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Amazon Marketing Cloud tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "amazon-marketing-cloud-mcp-client",
  servers: {
    "amazon-marketing-cloud-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Amazon Marketing Cloud Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Amazon Marketing Cloud tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Amazon Marketing Cloud transactions"
);
console.log(result.text);

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 Mastra AI

Mastra uses its built-in workflow engine to catch failures from `create_execution`. It applies exponential backoff or routes the failure to an error-handling node that can modify the SQL query and try again.

Yes, you can configure Mastra's `requireToolApproval` on the `delete_workflow` tool. The agent pauses execution and waits for a manual confirmation before removing any SQL configurations from AMC.

You initialize the server via the `MCPClient` constructor, then spread the tools from `listTools()` into your Mastra Agent's tool array. The framework automatically registers the SQL and workflow management capabilities.

Yes, you can use Mastra's workflow engine to trigger `create_execution` on a cron schedule. The agent will run the query, monitor its status, and send the final download URLs to your database.

Vinkius manages the secure connection to your AWS clean room, isolating each run in a zero-trust V8 sandbox on the Vinkius MCP Server. Your sensitive SQL queries and schema metadata are never exposed to external networks or stored in plaintext.

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