Build JSON-Connected Applications in Kiro with CData Connect AI MCP Server

Kiro is an agentic AI IDE from AWS that takes a spec-driven approach to software development, turning a natural language prompt into a detailed spec, then into working code, tests, and documentation. Available as a desktop IDE and CLI, Kiro supports remote MCP servers natively across all plans, letting agents pull live context from enterprise systems while they build.

By integrating Kiro with CData Connect AI through the MCP (Model Context Protocol), Kiro agents gain the ability to query, analyze, and act on live JSON services directly inside any coding session. Connect AI manages authentication, security, and query optimization so you can focus on building intelligent applications, while Kiro handles spec generation, code writing, and task execution.

This article outlines the steps to configure JSON connectivity in Connect AI, generate the required authentication credentials, register the Connect AI MCP Server in Kiro, and verify that your agent can successfully interact with live JSON services during coding sessions.

Prerequisites

• Kiro account
• CData Connect AI account
• JSON account with valid credentials.

Step 1: Configure JSON Connectivity for Kiro

Connectivity to JSON from Kiro is made possible through Connect AI's Remote MCP Server. To interact with JSON services from your Kiro agent sessions, start by creating and configuring a JSON connection in 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 in the Add JSON Connection page and update the User-based permissions.

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Kiro. 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 (e.g., Kiro MCP) and click Create.

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

Step 2: Register the CData Connect AI MCP Server in Kiro

Kiro connects to external data sources through MCP servers configured in a file called mcp.json. In this step, you will open that file, add the Connect AI server details, and verify the connection.

1. Open a project folder. Kiro requires an open project before its agent features activate. When Kiro launches, click Open a project on the Getting started screen (or click Open Folder in the Explorer panel on the left). You can open any existing folder or create a new empty one, it just needs to be open.
2. Open the MCP config file. Press Ctrl + Shift + P (Windows) or Cmd + Shift + P (Mac) to open the command palette. Type MCP and select Kiro: Open user MCP config (JSON). This opens the mcp.json file where you register MCP servers for Kiro.
3. Generate your Base64 credentials. Kiro authenticates with Connect AI using your email and PAT, encoded together as a single Base64 string. Open a terminal and run the command for your operating system. Replace [email protected] with your Connect AI login email and YourPAT with the PAT you created in Step 1.

   Windows (PowerShell):

   [Convert]::ToBase64String([Text.Encoding]::UTF8.GetBytes("[email protected]:YourPAT"))

   Mac/Linux (Terminal):

   echo -n "[email protected]:YourPAT" | base64

   Copy the output string. You will paste it into the config file in the next step.

4. Add the Connect AI server to mcp.json. Paste the following block into your mcp.json file. Replace your_base64_string with the string you copied in the previous step:

   {
     "mcpServers": {
       "cdata-connect-ai": {
         "url": "https://mcp.cloud.cdata.com/mcp",
         "headers": {
           "Authorization": "Basic your_base64_string"
         }
       }
     }
   }    

   
5. Save the file. Press Ctrl + S (Windows) or Cmd + S (Mac). Kiro picks up changes to mcp.json automatically, no restart is needed.
6. Verify the connection. Click the ghost icon in the left sidebar to open the Kiro panel. Under MCP SERVERS, you should see cdata-connect-ai with a green connected indicator. You can also confirm by typing the following in the Kiro chat panel:

   List all available connections from Connect AI.

   If your JSON connection appears in the response, the MCP server is set up correctly and you are ready to query live data.

   

Step 3: Query Live JSON Services from Kiro

With the MCP server registered and verified, Kiro agents can now access your live JSON services directly in any session. Open the Kiro chat panel and use the following prompts to interact with your data.

The integration uses the following Connect AI MCP tools in sequence:

Open the Kiro chat panel and try the following prompts to interact with your JSON services:

• "What tables are available in my JSON connection?"
• "What are the top records in JSON services ordered by revenue?"
• "List all active JSON services and their current status."
• "Summarize JSON services activity for this quarter."

Kiro automatically discovers all CData connections, selects the most relevant connection, discovers the schema, generates, and executes the appropriate SQL query, and returns live results directly in the chat.

Build real-time, data-aware applications with Kiro and CData

Kiro and CData Connect AI together enable intelligent, AI-driven development where natural language prompts are automatically translated into live data operations across enterprise systems, without ETL pipelines, data sync jobs, or custom integration logic. This streamlined approach delivers stronger governance, lower operational overhead, and faster, more grounded responses from AI-powered agents.

Start a free trial today to see how CData Connect AI can empower Kiro with live, secure access to hundreds of enterprise systems.