BlueXP™ workload factory for AWS (workload factory) is here to help orchestrate and automate workloads for your Amazon FSx for NetApp ONTAP (FSx for ONTAP) data. With many different capabilities, workload factory GenAI is used to bring enterprise data into generative artificial intelligence (GenAI) architectures. Together with Amazon Bedrock, workload factory can easily set up retrieval-augmented generation (RAG) pipelines.
Amazon Q Developer is an agentic coding experience that helps you accomplish your tasks easily. It automatically reads and writes files locally, generates code diffs, and runs shell commands, while incorporating your feedback and sending real-time updates along the way. It’s built to enrich coding experience and improve developer productivity and uses native information and data and APIs across MCP server-based tools to do this.
MCP, or Model Context Protocol, is an open standard developed by Anthropic to streamline how large language models (LLMs) integrate with external tools, data, and other systems. It essentially acts as a universal bridge, allowing LLMs to access and utilize information from various sources in a consistent and secure way
This post will guide you on how to set up and operate workload factory GenAI to create a knowledge base, connect it to your data sources, that contain your organization software internal documentation (In our case Workload Factory AI documentation) on FSx for ONTAP, and make it accessible to your Amazon Q Developer agent using MCP to improve developer productivity.
The following steps walk you through the process in its centralized user flow:
Step 1: Deploy GenAI infrastructure
Step 2: Create your first knowledge base
Step 4: Configure MCP server for Knowledge base
Step 5: Make sure the client is running on your workstation
Step 6: Configure MCP server in Amazon Q Developer
Step 7: Chat with Amazon Q CLI
Step 8: Configure VS Code Extension
Step 9: Chat with Amazon Q Extension using Workload Factory MCP Server
Knowledge base Walkthrough
Step 1: Deploy your GenAI infrastructure
First, go to the workload factory home page. Log in with an existing workload factory account or sign up to create a new one.
Workload factory is used to deploy and manage a variety of different workloads. Workload factory GenAI is located in the AI section of the workload factory home page.
Go to the navigation menu on the left and select the GenAI icon (the chip shape).
Another way to do this is to select “Deploy & manage” from the options in the AI section of the workload factory homepage.
Read the Introduction on the next screen, then click "Get started" to deploy GenAI infrastructure.
Step 2: Create your first knowledge base
Once you’ve deployed Workload factory GenAI in your account will start you off by asking to create a knowledge base for your data.
A knowledge base consists of one or more data sources on FSx for ONTAP , on-premises ONTAP The data or a NFS\SMB volume within the knowledge base is an embedding representation of your source data, automatically stored under the hood in a vector database. This data can then be used to augment prompts from the GenAI application.
To get started, click the “Next” button.
In the next screen you’ll be asked to define the details of your knowledge base.
You can leverage advance models from Amazon Bedrock as well as enable data guardrail to omit private information.
Click on each of the sections to configure the knowledge base. Here’s a look at each of them.
- First, you’re prompted to give your knowledge base a name.
- Next, provide a description of the knowledge base. This will help understand the data within the MCP server context.
- Now, define the embedding model the knowledge base will rely on.
- Next, add a Chat model.
- Next, Select your Reranking method and model
- Next, select if you would like to activate Data guardrails, conversation starters and define your storage destination and snapshot policy for your knowledge base.
Once you have all the correct information about the knowledge base entered, click the “Create Knowledge base” button.
Step 3: Add an FSx for ONTAP data source
Workload factory GenAI lets you add FSx for ONTAP volumes as data sources for your RAG’s knowledge base.
- You’ll now be in the “Add data source” screen, where you’ll be prompted to select one or more file systems from a list of available FSx for ONTAP file systems. (Note: If you haven’t set up an FSx for ONTAP file system before, here are the instructions.) Select the file system(s) that you want the GenAI application to access, and click “Next.”
- In the next screen, select one or more volumes where your private data is stored.
- In the next screen, you’ll be asked to select a data source. You can either choose to embed the entire volume or specific folders in the selected volume(s).
- If you choose the option for specific folders, you’ll be presented with a list of all the folders that reside in the volume. Select each of the folders you want to use for the knowledge base.
- Next, you can define the parameters for the embedding model that will be used to create embedding vectors for your data sources. Here, you can choose how data is being chunked and stored in the vector database.
- Once your data source is added, you will now see it is listed for the corresponding knowledge base under the workload factory GenAI screen.
- From here, you can view and manage this knowledge base and any others that you create. Find the knowledge base you want to manage in the list and click the three-dot menu icon to its right. Then select the “Manage Knowledge base” option from the drop down menu.
- This opens a screen where you can view the details of the knowledge base and add more data sources
Step 4: Configure MCP server for Knowledge base
Before starting the configuration, ensure the following prerequisites are met:
BlueXP Service Account: A service account must be created within your BlueXP tenancy account.
The BlueXP service account provides programmatic access to BlueXP services, enabling applications like the MCP server to authenticate and interact with your resources. This can be created from the "Identity & access management" section in the BlueXP console.
After creating the service account, note down the Client ID and Client Secret as they are not stored on the platform.
Learn more here:
- https://docs.netapp.com/us-en/bluexp-setup-admin/task-managing-netapp-accounts.html#create-and-manage-service-accounts
- https://docs.netapp.com/us-en/bluexp-automation/platform/register_service.html
Using Knowledge base MCP in Amazon Q Developer
Step 5: Make sure the client is running on your workstation
After installing the client on the prerequisites make sure it’s running on your workstation. Get into settings and make sure everything is up and running.
Step 6: Configure MCP server in Amazon Q Developer
Download and build the Workload Factory MCP server from here.
To configure the WF MCP server for Amazon Q you’ll need to edit this file on your workstation: ~/.aws/amazonq/mcp.json
The file should contain the MCP configuration JSON including the path to the server executable and the login parameters file (make sure you download and build it following the instructions in the prerequisites):
{
"mcpServers": {
"workload-factory-gen-ai": {
"command": "node",
"args": [
"--env-file=/projects/wlm-ai/mcp-server/config/config.env",
"/projects/wlm-ai/mcp-server/build/index.js"
]
}
}
}
After you configure the server, you can verify the configuration using the following cli command;
Step 7: Chat with Amazon Q CLI
You can start chatting with Q CLI by using the q chat cli command. Notice that when the chat loads it identifies the new MCP tool.
If you ask a question that will require usage of the Knowledge base data the Amazon Q agent will use the Workload Factory MCP tool to resolve it.
Step 8: Configure VS Code Extension
Load your VS Code IDE and make sure you installed the Amazon Q extension as required. Load the Amazon Q chat from the left side panel and select the Configure MCP Servers on the top left part of the chat.
Once you get into the MCP Server configurations you should see the Workload Factory MCP server we created on previous steps for the CLI. The Amazon Q extension already finds the configuration on the mcp.json file and loads it.
You should now be able to start working and chatting using the Workload Factory MCP tool. If you need to change the configuration you can do that from the Amazon Q extension by selecting on the configuration.
Step 9: Chat with Amazon Q Extension using Workload Factory MCP Server
Now you should be able to chat freely using the Amazon Q chat and retrieve data or create code parts based on the documentation you store on your FSxN file system. When the MCP tool is used the Amazon Q chat will prompt you about the usage.
Conclusion
By following these steps, you can deploy and configure the NetApp Workload Factory GenAI MCP server, allowing your published knowledge bases to interact with external MCP clients like Claude Desktop and Q for developer CLI. This functionality is important for integrating organizational knowledge GenAI with minimal overhead, along with the Workload Factory GenAI which provides a quick, no-code method to set up a knowledge base using your organizational data on ONTAP.
To get started, get more details in our documentation and download the MCP server from our GitHub repository and release blog.
