How to Use the Amazon Marketing Cloud MCP in LangChain

Q: How do I handle slow SQL queries when using Amazon Marketing Cloud with LangChain?

Use getexecutionstatus inside a LangChain loop to poll for results. If the query hangs, call deleteexecution to kill it before your agent times out.

Q: Can my LangChain agent dynamically modify Amazon Marketing Cloud workflows?

Yes, the agent can call listworkflows to find the target ID, then use updateworkflow to change the SQL query. LangChain chains pass the updated schema directly to the next execution step.

Q: How does LangChain trace Amazon Marketing Cloud tool calls?

Every call to createexecution or getexecutiondownloadurls is logged in LangSmith. You get full visibility into the exact SQL sent to the MCP Server and the execution times.

Q: How do I run multiple AMC queries in parallel?

Use LangChain's async batching with createexecution. The server handles the concurrent requests, and you can poll their statuses together using listexecutions.

Run SQL queries on Amazon Marketing Cloud and trace every execution inside your LangChain pipelines using this MCP Server.

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 LangChain

Create your Vinkius account to connect Amazon Marketing Cloud to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run and monitor AMC queries dynamically

The `create_execution` tool lets your LangChain agent run raw SQL queries directly against your Amazon Marketing Cloud clean room. Your agent triggers the query, gets the execution ID, and then passes that ID to `get_execution_status` in a loop until it completes. This prevents silent failures when your agent tries to tweak complex SQL joins using this MCP integration.

Manage complex AMC workflows with LangChain agents

You can build, update, and inspect your database of queries using `create_workflow` and `update_workflow`. Instead of hardcoding SQL templates, your LangChain chain inspects existing setups with `list_workflows` and decides whether to modify them. If a workflow becomes obsolete, the agent calls `delete_workflow` to keep your workspace clean.

Pull clean room data into LangChain memory

The `get_execution_download_urls` tool fetches the secure S3 paths containing your Amazon Marketing Cloud query results. Your LangChain agent handles the download and parses the CSV data to feed downstream tools or memory buffers. If a run takes too long, `delete_execution` stops it immediately to keep your LangChain loops fast.

Setup guide

Set up Amazon Marketing Cloud MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Amazon Marketing Cloud tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "amazon-marketing-cloud-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Amazon Marketing Cloud transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use `get_execution_status` inside a LangChain loop to poll for results. If the query hangs, call `delete_execution` to kill it before your agent times out.

Yes, the agent can call `list_workflows` to find the target ID, then use `update_workflow` to change the SQL query. LangChain chains pass the updated schema directly to the next execution step.

Every call to `create_execution` or `get_execution_download_urls` is logged in LangSmith. You get full visibility into the exact SQL sent to the MCP Server and the execution times.

Use LangChain's async batching with `create_execution`. The server handles the concurrent requests, and you can poll their statuses together using `list_executions`.

Your SQL query results and download URLs stay inside your private environment. Vinkius runs the MCP Server in an isolated V8 sandbox, meaning no advertising data is ever stored or leaked.

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