Amazon Marketing Cloud MCP. Run complex ad analytics and manage SQL workflows.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Amazon Marketing Cloud MCP Server handles advanced advertising analytics. It lets your AI agent execute complex SQL queries and manage data workflows against your AMC instance.
You can list, create, and update workflows, run ad-hoc queries, and retrieve secure S3 download URLs—all via natural conversation. It keeps your data pipelines inside the secure AMC environment.
What your AI agents can do
Create execution
Starts a new, immediate query execution against the Amazon Marketing Cloud data.
Create workflow
Builds and saves a new, structured SQL workflow template within AMC.
Delete execution
Cancels a running or pending execution job to stop unnecessary processing.
The agent executes ad-hoc SQL queries against your AMC data using the create_execution tool.
The agent lists, creates, and updates defined SQL workflows using list_workflows, create_workflow, and update_workflow.
The agent checks if an execution is PENDING or COMPLETED using get_execution_status.
The agent fetches the secure S3 download URL for completed reports using get_execution_download_urls.
The agent lists past executions (list_executions) and allows you to delete or cancel running jobs.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Amazon Marketing Cloud MCP Server: 10 Tools for Ad Analytics
These 10 tools let your AI agent manage every aspect of your AMC data pipeline—from creating reports to retrieving final S3 download links.
019d754ccreate execution
Starts a new, immediate query execution against the Amazon Marketing Cloud data.
019d754ccreate workflow
Builds and saves a new, structured SQL workflow template within AMC.
019d754cdelete execution
Cancels a running or pending execution job to stop unnecessary processing.
019d754cdelete workflow
Removes a saved SQL workflow template from the Amazon Marketing Cloud system.
019d754cget execution download urls
Retrieves the secure S3 link needed to download the results of a finished query.
019d754cget execution status
Checks the current status (PENDING, COMPLETED, etc.) of any specific execution ID.
019d754cget workflow details
Fetches detailed metadata about a specific, saved SQL workflow template.
019d754clist executions
Shows a list of recent and past workflow executions for auditing purposes.
019d754clist workflows
Retrieves a list of all available, saved SQL workflow templates in your AMC instance.
019d754cupdate workflow
Modifies the parameters or structure of an existing, saved SQL workflow.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Amazon Marketing Cloud, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Yo, this Amazon Marketing Cloud MCP Server lets your AI agent run serious advertising analytics without you having to mess with the AWS console. It manages your whole data pipeline just through talking to it. You'll use it to run complex SQL queries, build whole workflows, and grab the final report URLs—all from your chat window.
Running SQL Queries
When you need to run a one-off query, your agent uses create_execution to start an immediate job against your AMC data. If you need to check what's going on, it uses get_execution_status to tell you if the job's PENDING or COMPLETED. You can also pull a list of past jobs with list_executions, and if something stalls, you can kill it with delete_execution.
Once a query finishes, your agent pulls the secure S3 link with get_execution_download_urls, so you can download the report right away.
Managing Workflows
Want to standardize reports? Your agent handles that. You can see all your saved templates using list_workflows, or you can grab the full details of a specific template with get_workflow_details. If you need to build a new standard report, it uses create_workflow to build and save a new SQL workflow template.
You can then tweak that template later by running update_workflow, and if the template is garbage, you can wipe it clean with delete_workflow.
This setup lets your agent keep all your data pipelines locked inside the secure AMC environment. It's pure SQL power, delivered straight to your chat.
How Amazon Marketing Cloud MCP Works
- 1 First, you subscribe to the server and provide your AMC Instance ID, Amazon Ads Client ID, and necessary tokens.
- 2 Next, you tell your agent what you need—for example, 'Run the Campaign Overlap Analysis workflow for last month.'
- 3 The agent uses
create_execution(or a workflow tool) and, once complete, usesget_execution_download_urlsto give you the report link.
The bottom line is, your AI client talks to the server, and the server executes the complex logic inside your Amazon Marketing Cloud account.
Who Is Amazon Marketing Cloud MCP For?
This is for data analysts, media buyers, and marketing engineers. If your job involves complex, multi-touch attribution reporting or managing SQL data pipelines, this tool gets the job done. Stop jumping between the AWS console and your analysis tools.
Runs ad-hoc queries to figure out how different channels influenced a conversion, checking for audience overlap without writing complex API calls.
Automates the execution of recurring, complex SQL queries and retrieves the results for immediate review.
Manages the configuration of AMC workflows, verifying API execution statuses on the fly and auditing the system's activity.
What Changes When You Connect
- Run complex multi-touch attribution queries without leaving the chat. You trigger these analyses directly using
create_execution, which handles the entire process inside AMC. - Stop manual workflow setup. Use
list_workflowsandcreate_workflowto define, standardize, and save your recurring SQL reports. - Save time waiting for results. You can check the progress of long jobs using
get_execution_statusand cancel stalled queries immediately withdelete_execution. - Get reports instantly. Once a job finishes, use
get_execution_download_urlsto get the secure S3 link right in the chat, skipping the AWS console download process. - Maintain data integrity. You can audit everything by running
list_executionsto see the history and confirming exactly when a query ran and what its status was.
Real-World Use Cases
Analyzing Campaign Overlap
A media buyer needs to know if two different campaigns are targeting the same audience segments. They ask their agent to run a specific workflow. The agent calls create_execution and, once the job is done, uses get_execution_download_urls to deliver the overlap report.
Auditing Reporting Failure
A data analyst notices a report is missing and needs to know why. They ask the agent to run list_executions to see the job history. They then use get_execution_status on the specific ID to determine if the failure was due to bad data or a system issue.
Updating Standard Reports
A marketing engineer changes the definition of a successful path-to-conversion workflow. Instead of manually modifying the console, they use update_workflow to change the parameters, then use create_execution to test the new version immediately.
Mass Data Retrieval
An advertising strategist needs 5 reports for different time periods. They don't run them all at once. They use list_workflows to find the correct templates, run create_execution for each, and then batch-retrieve the results using get_execution_download_urls.
The Tradeoffs
Over-relying on manual console navigation
A user manually navigates the AWS console, clicks through multiple tabs, and copies SQL query parameters into a separate spreadsheet. This is slow and error-prone.
→
Let your agent handle the process. Use list_workflows to find the correct template, then trigger the run with create_execution. The agent handles the data flow and status tracking for you.
Assuming immediate results
A user runs a complex query and immediately assumes the results are available, leading to frustration when the job is still PENDING or times out.
→
Always check the status. Use get_execution_status to poll the job ID. Only request the final data when the status is 'COMPLETED', then call get_execution_download_urls.
Creating redundant reports
A team member runs the same complex attribution query multiple times because they aren't sure if the previous run succeeded or if the parameters were correct.
→
First, use list_workflows to review saved templates. Then, use update_workflow if parameters changed, and finally use create_execution to run the clean, controlled job.
When It Fits, When It Doesn't
Use this server if your primary pain point is cross-channel advertising analytics and you need to manage complex, stateful SQL data pipelines. You need to run multi-step processes (define, execute, monitor, download) without ever leaving your AI chat client.
Don't use this if your needs are simple: If you only need to view static reports or perform basic filtering, a simple dashboard tool is fine. If you need to interact with a completely different data source (e.g., Salesforce records), use a dedicated integration server for that instead. This server is specialized for AMC data only. Always check the get_workflow_details before running create_execution to ensure the template is correct.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
The current process for running cross-channel analytics is a nightmare of clicks.
Right now, getting a full view of multi-touch attribution means logging into the AWS console. You have to find the right workflow template, manually input date ranges, click 'run,' and then wait in a separate monitoring tab, constantly refreshing the status until it eventually completes. It's a lot of clicking and refreshing.
With this MCP server, you just tell your agent what you need. It handles the workflow orchestration. You use `create_execution`, and your agent manages the wait time, giving you a clear status update and eventually retrieving the final report via `get_execution_download_urls`.
Amazon Marketing Cloud MCP Server: Get the data you need, instantly.
You eliminate the need to manually navigate workflow IDs, verify API credentials, or track job status in separate dashboards. Your agent handles all the metadata work—you just talk to it.
It means complex data pipelines are now triggered and monitored entirely through simple chat commands. No more console jumping. Period.
Common Questions About Amazon Marketing Cloud MCP
How do I check the status of a job using the get_execution_status tool? +
You provide the execution ID to the get_execution_status tool. It returns the current state (e.g., PENDING, COMPLETED). If it's COMPLETED, you'll then need to call get_execution_download_urls.
Can I list my saved workflows with list_workflows? +
Yes, list_workflows retrieves all available, saved SQL workflow templates from your AMC instance. This lets you see what reports are already configured.
What's the difference between create_execution and create_workflow? +
The create_workflow tool builds the template (the definition) of a reusable report. The create_execution tool actually runs that template, generating the data and the job ID.
How do I cancel a running query using delete_execution? +
Use the delete_execution tool and pass the execution ID. This sends a cancellation request to AMC, stopping the job and freeing up resources.
Where do I find the final report using get_execution_download_urls? +
What should I use to manage or modify an existing workflow using update_workflow? +
The update_workflow tool modifies existing AMC workflows. You pass the specific workflow ID and the new configuration parameters to change how it runs.
How do I list past job runs or track history using list_executions? +
The list_executions tool fetches a list of your completed or running job runs. You get a summary of the execution IDs, start times, and status for auditing purposes.
Do I need to run a workflow first before I can execute an ad-hoc query using create_execution? +
No. You can run ad-hoc queries directly using create_execution without defining a formal workflow. This is for one-off SQL analyses.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Amadeus
Search flights, hotels, transfers, and destination activities across 400+ airlines and 150,000+ hotels worldwide through natural conversation.
Notion
Manage your Notion workspace, databases, and pages via AI.
Nimbata
Track which marketing campaigns generate phone calls with dynamic number insertion and call attribution analytics.
You might also like
Gallabox
Automate WhatsApp Business communication, send templates, and manage chats via AI agents with Gallabox.
Atlassian (Jira & Confluence)
The ultimate AI bridge for Jira and Confluence — manage projects, agile boards, and wikis via AI.
Foursquare Alternative
Manage your location data — audit places, photos, and tips via AI.
