Access Live JSON Services in Roo Code via CData Connect AI

Roo Code is an open-source AI coding agent that runs inside VS Code with real file system access, terminal control, and multi-step workflows. It works across entire project workspaces through specialized modes like Code, Architect, and Orchestrator. Available as a VS Code Extension for local development, or as Cloud Agents that integrate with Slack and GitHub. Roo Code natively supports MCP, connecting external tools and data sources via STDIO or Streamable HTTP.

By default, Roo Code has no access to live enterprise data. CData Connect AI bridges this gap by exposing hundreds of data sources. Once connected, Roo can introspect live schemas, validate queries, and generate code directly inside VS Code, retrieved by real enterprise data.

Step 1: Configure JSON connectivity for Roo Code

Connectivity to JSON from Roo Code is made possible through CData Connect AI's Remote MCP Server. To interact with JSON services from Roo Code, start by creating and configuring a JSON connection in CData Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select JSON from the Add Connection panel

3. Enter the necessary authentication properties to connect to JSON.

   See the Getting Started chapter in the data provider documentation to authenticate to your data source: The data provider models JSON APIs as bidirectional database tables and JSON files as read-only views (local files, files stored on popular cloud services, and FTP servers). The major authentication schemes are supported, including HTTP Basic, Digest, NTLM, OAuth, and FTP. See the Getting Started chapter in the data provider documentation for authentication guides.

   After setting the URI and providing any authentication values, set DataModel to more closely match the data representation to the structure of your data.

   The DataModel property is the controlling property over how your data is represented into tables and toggles the following basic configurations.

   • Document (default): Model a top-level, document view of your JSON data. The data provider returns nested elements as aggregates of data.
   • FlattenedDocuments: Implicitly join nested documents and their parents into a single table.
   • Relational: Return individual, related tables from hierarchical data. The tables contain a primary key and a foreign key that links to the parent document.

   See the Modeling JSON Data chapter for more information on configuring the relational representation. You will also find the sample data used in the following examples. The data includes entries for people, the cars they own, and various maintenance services performed on those cars.

   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Roo Code. It is best practice to create a separate PAT for each integration to maintain granular access control.

1. Click the gear icon at the top right of the Connect AI app to open Settings
2. On the Settings page, go to the Access Tokens section and click Create PAT
3. Give the PAT a descriptive name and click Create

4. Copy the token when displayed and store it securely. It will not be shown again

With the JSON connection configured and a PAT generated, Roo Code can now connect to JSON services through Connect AI.

Step 2: Configure Connect AI in Roo Code

CData Connect AI can be integrated with Roo Code by registering the MCP Server directly in the Roo Code MCP configuration panel. Once registered, Roo Code agents can call live JSON services through MCP tools without additional setup.

Method 1: Direct MCP configuration

Users can register the CData Connect AI MCP Server directly in the Roo Code MCP settings. Once registered, agents in any project can query live JSON services through MCP tools without additional setup.

1. Open VS Code with the Roo Code extension installed
2. Click the Roo Code icon in the Activity Bar
3. Navigate to Settings, then choose MCP Servers in the Roo Code pane and turn on Enable MCP Servers, now click Edit Global MCP to open the MCP configuration file
4. In the mcp_settings.json file, add the following inside the mcpServers object, replacing base64encode with your Base64-encoded email:PAT

   {
       "mcpServers": {
           "cdata-mcp": {
               "type": "streamable-http",
               "url": "https://mcp.cloud.cdata.com/mcp",
               "headers": {
                   "Authorization": "Basic base64encode(USERNAME:PAT)"
               }
           }
       }
   }
           

   
5. Save the file to register the MCP server
6. Return to the MCP Servers panel and confirm that cdata-mcp is listed and its toggle is enabled. If it is not enabled, toggle it on

With the CData MCP Server registered and enabled, Roo Code agents can now query and act on live JSON services through Connect AI in any project.

Query live JSON services from Roo Code

With the MCP server configured, start a conversation in the Roo Code chat panel to interact with live JSON services.

1. Open the Roo Code chat and enter a prompt to explore your data, for example:
   • List all available catalogs in my cdata-mcp connection.
   • Show the schemas and tables available for JSON.
   • Query the top 5 records from JSON services.
2. The agent calls the CData Connect AI MCP Server and returns live results from JSON services

Method 2: Build an application with natural language

Users can direct Roo Code to build a full application that connects to the CData Connect AI MCP Server through a natural language prompt. The agent gathers the required endpoint and credentials interactively, then generates a working application wired to live JSON services — all from the Roo Code chat panel inside VS Code.

1. Open the Roo Code panel in VS Code and select your preferred model from the dropdown
2. Enter a prompt that describes the application you want to build. For example:

   I would like to build a small application that connects to a remote MCP 
   HTTPS server. I already have the MCP endpoint URL and the required 
   credentials. The application should:
     - Establish a connection to the remote MCP server
     - Authenticate using the provided credentials
     - Retrieve and list all available catalogs from the MCP
   
   Please make sure the credentials are stored securely in a .env file
   and not hardcoded in the application.
           

3. Roo Code will prompt you to provide the MCP endpoint URL and authentication credentials. Supply the following values:
   • MCP Endpoint URL: https://mcp.cloud.cdata.com/mcp
   • Authorization: Basic base64(email:PAT)
4. Roo Code creates the project directory, initializes a Node.js project, installs the necessary packages, and stores credentials securely in a .env file

At this point, Roo Code has built an application that communicates with the CData Connect AI MCP Server and retrieves live JSON services, all from a single natural language prompt inside VS Code.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources directly from Roo Code, try CData Connect AI today! Sign up for a free 14-day trial of CData Connect AI, and as always, our world-class Support Team is available to assist you with any questions you may have.