How to Use the Amazon Marketing Cloud MCP in LlamaIndex

Q: How does LlamaIndex index Amazon Marketing Cloud query results?

The agent calls getexecutiondownloadurls to retrieve the data files, then parses the CSVs into vector nodes. This lets you query your Amazon Marketing Cloud metrics using semantic search.

Q: Can LlamaIndex automatically select the right Amazon Marketing Cloud workflow?

Yes, by indexing the output of listworkflows into a vector store. The agent performs a semantic search over your workflows to find the exact ID it needs.

Q: How do I handle failed Amazon Marketing Cloud executions in LlamaIndex?

Your agent checks getexecutionstatus during its query loop. If it detects a failure, it can read the error or call deleteexecution to clean up the run.

Q: How do I add new SQL workflows to the index?

Use createworkflow to save a new SQL query to AMC. LlamaIndex then updates its index by calling listworkflows to fetch the new metadata.

Index Amazon Marketing Cloud query results directly into LlamaIndex vector stores for RAG-powered ad analysis via MCP.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn live AMC query results into searchable knowledge

The `get_execution_download_urls` tool pulls raw advertising data from completed Amazon Marketing Cloud runs so LlamaIndex can index it. Your LlamaIndex agent downloads the query results and parses them into Document nodes. By indexing these nodes, your RAG pipeline can answer complex questions about ad performance using real, historical clean room metrics.

Search and manage marketing workflows via LlamaIndex

Use `list_workflows` to retrieve your entire library of Amazon Marketing Cloud queries and index their metadata. When a user asks a query-related question, LlamaIndex searches this index to find the right workflow ID instead of guessing. If the agent needs to inspect a specific query, it calls `get_workflow_details` to feed the SQL schema into its prompt context.

Run and track SQL executions using LlamaIndex agents

The `create_execution` tool initiates SQL queries directly from your LlamaIndex query engine. While the query runs, `get_execution_status` tracks its progress in the background. If a run fails or stalls, the agent triggers `delete_execution` to free up resources, making it the cleanest way to run queries on this MCP Server.

Setup guide

Set up Amazon Marketing Cloud MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Amazon Marketing Cloud MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Amazon Marketing Cloud tools.",
)
response = await agent.run("List recent Amazon Marketing Cloud data")

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 LlamaIndex

The agent calls `get_execution_download_urls` to retrieve the data files, then parses the CSVs into vector nodes. This lets you query your Amazon Marketing Cloud metrics using semantic search.

Yes, by indexing the output of `list_workflows` into a vector store. The agent performs a semantic search over your workflows to find the exact ID it needs.

Your agent checks `get_execution_status` during its query loop. If it detects a failure, it can read the error or call `delete_execution` to clean up the run.

Use `create_workflow` to save a new SQL query to AMC. LlamaIndex then updates its index by calling `list_workflows` to fetch the new metadata.

Yes, all advertising SQL schemas and S3 download URLs are processed in memory within your private LlamaIndex instance. The Vinkius MCP Server runs in a zero-trust, ephemeral sandbox that never caches your credentials or advertising metrics.

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