Integrating Boomi Agentstudio with Adobe Commerce Data via CData Connect AI

Boomi Agentstudio is an enterprise platform for designing, orchestrating, and governing AI agents that automate tasks, enhance integration workflows, and support intelligent decision making across business processes. When you connect it with CData Connect AI, Boomi Agentstudio can securely access, query, and act on live enterprise data such as Adobe Commerce through a standardized MCP tool interface.

CData Connect AI is a managed Model Context Protocol (MCP) platform that provides governed, real-time access to enterprise data systems. It exposes structured metadata, including catalogs, schemas, tables, and SQL querying across hundreds of data sources. With Connect AI, Boomi Agentstudio can incorporate live operational data directly into agent logic and workflow automation, eliminating the need for ETL pipelines, data replication, or custom integration code.

This article explains how to connect Boomi Agentstudio to a CData Connect AI MCP endpoint, configure access to your Adobe Commerce or any other supported data source, and begin issuing real-time queries from within your agent-driven workflows.

Prerequisites

• An account in Adobe Commerce.
• An account in CData Connect AI
• An account of Boomi Agentstudio.

Step 1: Configure Adobe Commerce connectivity for Boomi Agentstudio

For Boomi Agentstudio to access Adobe Commerce, create a connection to Adobe Commerce in CData Connect AI. This connection is then exposed to Boomi using the remote MCP server.

1. Log in to Connect AI click Sources, and then click + Add Connection 👁 Adding a Connection
   
2. From the available data sources, choose Adobe Commerce 👁 Selecting a data source
   
3. Enter the necessary authentication properties to connect to Adobe Commerce

   Adobe Commerce uses the OAuth 1 authentication standard. To connect to the Adobe Commerce REST API, obtain values for the OAuthClientId, OAuthClientSecret, and CallbackURL connection properties by registering an app with your Adobe Commerce system. See the "Getting Started" section in the help documentation for a guide to obtaining the OAuth values and connecting.

   You will also need to provide the URL to your Adobe Commerce system. The URL depends on whether you are using the Adobe Commerce REST API as a customer or administrator.

   • Customer: To use Adobe Commerce as a customer, make sure you have created a customer account in the Adobe Commerce homepage. To do so, click Account -> Register. You can then set the URL connection property to the endpoint of your Adobe Commerce system.

   • Administrator: To access Adobe Commerce as an administrator, set CustomAdminPath instead. This value can be obtained in the Advanced settings in the Admin menu, which can be accessed by selecting System -> Configuration -> Advanced -> Admin -> Admin Base URL.

     If the Use Custom Admin Path setting on this page is set to YES, the value is inside the Custom Admin Path text box; otherwise, set the CustomAdminPath connection property to the default value, which is "admin".

   👁 Configuring a connection (Salesforce is shown)
   
4. Click Create & Test
5. Once authenticated, open the Permissions tab in the Adobe Commerce connection and configure user-based permissions as required 👁 Updating permissions
   

Generate a Personal Access Token (PAT)

Boomi Agentstudio authenticates to Connect AI using an account email and a Personal Access Token (PAT). Creating separate PATs for each integration is recommended to maintain access control granularity.

1. In Connect AI, select the Gear icon in the top-right to open Settings
2. Under Access Tokens, select Create PAT
3. Provide a descriptive name for the token and select Create 👁 Creating a new PAT
   
4. Copy the token and store it securely. The PAT will only be visible during creation

With the Adobe Commerce connection configured and a PAT generated, Boomi Agentstudio is ready to connect to Adobe Commerce data via the CData Connect AI MCP server.

Step 2: Create a source using the CData Connect AI MCP endpoint

Start by creating a new MCP data source inside Boomi Agentstudio. This establishes a secure connection between Boomi and CData Connect AI, allowing agents to call MCP tools and work with live enterprise data.

To connect with Connect AI MCP as a source, follow the given process:

1. Log in to Boomi.
2. Open Services and select Agentstudio from the list. 👁 Select Agentstudio from Services list.
   
3. Go to the Sources tab and click Create a new source. 👁 Create a new source.
   
4. In the Agent Designer window, open the Sources tab and choose Model Context Protocol (MCP) as the source type. 👁 Select Model Context Protocol (MCP) as a source.
   
5. On the Create MCP Source screen, enter the following Configuration details:
   • Name: Provide a name for the source
   • Details: Add a short description for the source
   • Transport Type: Streamable HTTP
   • URL: https://mcp.cloud.cdata.com/mcp
   • Authentication: Basic Authentication
   • Username: Enter your Connect AI account username
   • Password: Enter your Connect AI PAT
6. Click Test Connection. 👁 Enter the configuration details for the source (Connect AI).
   
7. After you establish a successful connection, click Discover Tools. Boomi lists all MCP tools exposed by CData Connect AI, including queryData, getCatalogs, getSchemas, and getTables, along with the remaining tools, in the Tools tab.
8. Select all tools in the Discover and Select Tools section and click Continue. 👁 Discover and select the tools.
   
9. In the Review section, verify the details and click Save. 👁 Review the configuration and tools for the source.
   

Boomi adds the new source to the Sources tab.

👁 The new source is created.

Click the Tools tab to confirm that all tools from CData Connect AI appear in the list.

👁 All the tools from CData Connect AI appear in the list.

Step 3: Create a new agent

Create a new agent to interact with your Adobe Commerce data. The agent acts as the interface between your prompts and the tools exposed by Connect AI, enabling it to process queries and return intelligent responses.

1. Go to the Agents tab and click Create New Agent. 👁 Create a new agent.
   
2. In the Agent Designer window, select Blank Template under the Agents tab. 👁 Select the Blank Template option from the Agents tab.
   
3. In the Profile section, enter the following details:
   • Basic Information: Specify the goal, agent name, and agent picture.
   • Agent Mode: Select either Conversational or Structured mode based on how you want the agent to respond to prompts, and configure the mode accordingly.
4. Click Save and Continue. 👁 Complete the Profile section.
   
5. In the Tasks section, define the actions your agent will perform:
   1. Click + Add New Task. 👁 Add a new task.
      
   2. In the Description tab, enter the task name and description. 👁 Add a name to the task along with a description.
      
   3. In the Instructions tab, click + Add New Instruction and describe how the agent should use the tool within this task. 👁 Add necessary instructions to the task.
      
   4. In the Tools tab, click + Add New Tool and select the tools exposed by Connect AI. Click Update Selected Tool, enable Requires Approval and Data Passthrough, save the task, and click Save and Continue. 👁 Select a tool from the list for the task.
      👁 The new task is added.
      

   Note: You can add up to 25 tools across all tasks.

6. In the Guardrails section, define the rules, restrictions, and filters to ensure your agent operates securely and ethically. Add a blocked message, denied topics, word filters, and custom regex patterns as required. Click Save and Continue. 👁 Add a guardrail.
   
7. In the Review section, verify all details and click Deploy to deploy the agent. 👁 Review the agent details and deploy the agent.
   

After you deploy the agent, use it to generate accurate and contextual responses to your prompts in the chat interface. 👁 The new agent is deployed.

Step 4: Prompt the Adobe Commerce data using the agent

After you create and deploy your agent, interact with your Adobe Commerce data using natural language prompts.

Follow these steps to prompt your Adobe Commerce data:

1. Go to the Chat tab and select your agent from the dropdown list. 👁 Select your agent from the agent list in the chat.
   
2. Enter a prompt (for example, "How many tables are available in Adobe Commerce?"). 👁 Enter a prompt.
   
3. The agent processes your prompt and returns the results. 👁 The agent processes your prompt and returns the desired result.
   

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!