Integrate Google's Antigravity Agent with Live Google Search Data via CData Connect AI

Antigravity is an AI-native development environment designed around autonomous and semi-autonomous agents. It allows developers to run agent-driven workflows directly inside the editor, combining planning, execution, and tool usage in a single interface.

By integrating Antigravity with CData Connect AI through the built-in MCP (Model Context Protocol) Server, agents gain governed, real-time access to live Google Search results. This enables Antigravity agents to explore schemas, query data, and perform actions without manual data movement or custom API wiring.

This article explains how to configure Google Search connectivity in Connect AI, generate the required access token, register CData Connect AI in Antigravity, and validate the integration by querying live Google Search results from an agent-driven workflow.

Step 1: Configure Google Search connectivity for Antigravity

Connectivity to Google Search from Antigravity is made possible through CData Connect AI's Remote MCP Server. To interact with Google Search results from Antigravity, start by creating and configuring a Google Search connection in CData Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection
👁 Adding a connection in Connect AI

2. Select Google Search from the Add Connection panel
👁 Selecting data source

3. Enter the necessary authentication properties to connect to Google Search.

   To search with a Google custom search engine, you need to set the CustomSearchId and ApiKey connection properties.

   To obtain the CustomSearchId property, sign into Google Custom Search Engine and create a new search engine.

   To obtain the ApiKey property, you must enable the Custom Search API in the Google API Console.

   👁 Configuring a connection (Salesforce is shown)
   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions
👁 Updating permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Antigravity. 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
👁 Creating a new PAT

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

With the Google Search connection configured and a PAT generated, Antigravity can now connect to Google Search results through CData Connect AI.

Step 2: Configure Connect AI in Antigravity

Next, register Connect AI in Antigravity. Antigravity reads MCP server definitions from a raw configuration file, allowing agents to dynamically discover and invoke the sources exposed by Connect AI.

1. Download the Antigravity desktop application and sign in using your Google account
2. During the initial setup flow, select Agent-driven development when prompted. This mode enables autonomous agents with tool execution capabilities 👁 Selecting agent-driven development
   
3. Once you have completed the Antigravity setup and the IDE is open, you can access the built-in agent interface to manage MCP servers. From the top menu, click Toggle Agent or press Ctrl + Alt + B to open the agent panel
4. Once the agent panel opens, click the "..." and select MCP Servers from the dropdown 👁 Selecting MCP Servers
   
5. Select Manage MCP Servers from the MCP Store, and click View raw config to open the MCP configuration file 👁 Selecting
   
6. Paste the following json into the file:

   {
    "mcpServers": {
    "cdata-mcp": {
    "serverUrl": "https://mcp.cloud.cdata.com/mcp",
    "headers": {
    "Authorization": "Basic your_base64_encoded_email_PAT",
    "Content-Type": "application/json"
    }
    }
    }
   }
   		

   Note: Antigravity will use Basic authentication with Connect AI. Combine your Connect AI user email and the PAT you created earlier and base64 encode the value. For example, given username and PAT like [email protected]:ABC123...XYZ789, the value for the Authorization header is something like: Basic dXNlckBteWRvbWFpbjphSzkvbVB4Mi9Rcjd2TjQvTHc4Qi96WTZqQzMvRnQ1SGcxL0RzMFVlL01iWHdKdg==

   👁 Editing the Config file
   
7. Save the configuration file
8. Return to the Manage MCP Servers view and click Refresh to load the new MCP server 👁 Configured Connect AI
   

Step 3: Query live Google Search results from Antigravity agent

With the MCP server registered, Antigravity agents can now interact with your live data sources exposed by Connect AI to explore schemas and run queries.

1. Open the agent panel again using Toggle Agent
2. Start a new conversation in the agent chat
3. Start interacting with the agent by entering prompts such as:
   • List all catalogs in my cdata-mcp connection.
   • Show schemas and tables available for Google Search.
   • Query the top 3 records from a table in Google Search results.
   👁 Querying CData MCP from Antigravity
   

At this point, your Antigravity agent communicates with the CData Connect AI MCP Server and retrieves live Google Search results through remote MCP tools.

Get CData Connect AI

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