Integrating Boomi Agentstudio with Bitbucket 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 Bitbucket 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 Bitbucket or any other supported data source, and begin issuing real-time queries from within your agent-driven workflows.

Prerequisites

• An account in Bitbucket.
• An account in CData Connect AI
• An account of Boomi Agentstudio.

Step 1: Configure Bitbucket connectivity for Boomi Agentstudio

For Boomi Agentstudio to access Bitbucket, create a connection to Bitbucket 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
2. From the available data sources, choose Bitbucket
3. Enter the necessary authentication properties to connect to Bitbucket

   For most queries, you must set the Workspace. The only exception to this is the Workspaces table, which does not require this property to be set, as querying it provides a list of workspace slugs that can be used to set Workspace. To query this table, you must set Schema to 'Information' and execute the query SELECT * FROM Workspaces>.

   Setting Schema to 'Information' displays general information. To connect to Bitbucket, set these parameters:

   • Schema: To show general information about a workspace, such as its users, repositories, and projects, set this to Information. Otherwise, set this to the schema of the repository or project you are querying. To get a full set of available schemas, query the sys_schemas table.
   • Workspace: Required if you are not querying the Workspaces table. This property is not required for querying the Workspaces table, as that query only returns a list of workspace slugs that can be used to set Workspace.

   Authenticating to Bitbucket

   Bitbucket supports OAuth authentication only. To enable this authentication from all OAuth flows, you must create a custom OAuth application, and set AuthScheme to OAuth.

   Be sure to review the Help documentation for the required connection properties for you specific authentication needs (desktop applications, web applications, and headless machines).

   Creating a custom OAuth application

   From your Bitbucket account:

   1. Go to Settings (the gear icon) and select Workspace Settings.
   2. In the Apps and Features section, select OAuth Consumers.
   3. Click Add Consumer.
   4. Enter a name and description for your custom application.
   5. Set the callback URL:
      • For desktop applications and headless machines, use http://localhost:33333 or another port number of your choice. The URI you set here becomes the CallbackURL property.
      • For web applications, set the callback URL to a trusted redirect URL. This URL is the web location the user returns to with the token that verifies that your application has been granted access.
   6. If you plan to use client credentials to authenticate, you must select This is a private consumer. In the driver, you must set AuthScheme to client.
   7. Select which permissions to give your OAuth application. These determine what data you can read and write with it.
   8. To save the new custom application, click Save.
   9. After the application has been saved, you can select it to view its settings. The application's Key and Secret are displayed. Record these for future use. You will use the Key to set the OAuthClientId and the Secret to set the OAuthClientSecret.
   
4. Click Create & Test
5. Once authenticated, open the Permissions tab in the Bitbucket connection and configure user-based permissions as required

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
4. Copy the token and store it securely. The PAT will only be visible during creation

With the Bitbucket connection configured and a PAT generated, Boomi Agentstudio is ready to connect to Bitbucket 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.
3. Go to the Sources tab and click Create a new source.
4. In the Agent Designer window, open the Sources tab and choose Model Context Protocol (MCP) as the source type.
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.
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.
9. In the Review section, verify the details and click Save.

Boomi adds the new source to the Sources tab.

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

Step 3: Create a new agent

Create a new agent to interact with your Bitbucket 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.
2. In the Agent Designer window, select Blank Template under 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.
5. In the Tasks section, define the actions your agent will perform:
   1. Click + Add New Task.
   2. In the Description tab, enter the task name and description.
   3. In the Instructions tab, click + Add New Instruction and describe how the agent should use the tool within this 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.

   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.
7. In the Review section, verify all details and click Deploy to deploy the agent.

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

Step 4: Prompt the Bitbucket data using the agent

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

Follow these steps to prompt your Bitbucket data:

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

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!