How to Connect JSON Services to Gemini Enterprise via CData Connect AI

Gemini Enterprise is Google's enterprise AI assistant, available as part of Google Workspace. With native support for Custom MCP Server data stores, Gemini Enterprise can be extended to query and act on live enterprise data via the Model Context Protocol (MCP). When combined with CData Connect AI Remote MCP, Gemini Enterprise can interact with JSON data in real time using natural language — without data replication or custom integration logic.

CData Connect AI offers a dedicated cloud-to-cloud interface for connecting to JSON data via a single managed MCP endpoint. The CData Connect AI Remote MCP Server enables secure communication between Gemini Enterprise and JSON, allowing users to ask questions and take actions on live JSON services through natural language prompts.

This article explains how to connect Gemini Enterprise to live JSON data through CData Connect AI by creating a Custom MCP Server data store — giving users access to JSON services directly from the Gemini Enterprise chat interface.

Prerequisites

1. A CData Connect AI account with at least one active connection (e.g., JSON)
2. A Gemini Enterprise account (trial available)
3. A Google Cloud project with billing enabled
4. The Google Cloud CLI installed and configured
5. In your Google Cloud account:
   • Override the organization policy for Custom MCP data stores (learn more).
   • Grant the Discovery Engine Editor role to the administrator (learn more).

Step 1: Configure JSON connectivity for Gemini Enterprise

Connectivity to JSON from Gemini Enterprise is made possible through CData Connect AI Remote MCP. To interact with JSON services from Gemini Enterprise, 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 in the Add JSON Connection page and update the User-based permissions.

Create an OAuth App in CData Connect AI

Gemini Enterprise uses OAuth 2.0 Authorization Code with PKCE to authenticate users against the CData Connect AI MCP Server. This requires creating a user-based OAuth App in your CData Connect AI account.

1. Click the Gear icon () in the top-right corner of Connect AI to open Settings.
2. Navigate to OAuth Apps and click + Create App. The Create OAuth App dialog appears.
3. Enter the following settings:
   • Name — Enter a descriptive name (e.g., GeminiEnterpriseOAuth).
   • Authentication Flow — Select User-based (Authorization Code).
   • Callback URL — Enter https://vertexaisearch.cloud.google.com/oauth-redirect.
   
4. Click Confirm. CData Connect AI creates the OAuth App and generates a Client ID and Client Secret.
5. Copy both the Client ID and Client Secret values. You will need them in Step 5.

With the connection configured and an OAuth App created, we are ready to create the custom MCP server data store in Gemini Enterprise.

Step 2: Create the custom MCP server data store

1. Open Gemini Enterprise and navigate to the Data stores screen.
2. Click Create data store.
3. On the Select a data source page, enter Custom MCP Server in the Search sources field. The Custom MCP Server card displays.
4. Click Add MCP server. The MCP Server Configuration page displays.
5. In the Authentication settings section, enter values in the following required fields:
   • MCP Server URL: https://mcp.cloud.cdata.com/mcp
   • Authorization URL: https://cloud-login.cdata.com/authorize
   • Token URL: https://cloud-login.cdata.com/oauth/token
   • Client ID and Client Secret: From the OAuth App created in Step 1
   
6. Click Login, and complete the sign-in.
7. Click Continue, and the Advanced options section opens.

8. In the MCP Server Description field, enter a description that helps Gemini Enterprise understand what the server does and when to use it. For more information, see Write effective MCP server descriptions and instructions.

9. Click Continue.

10. In the Configure your data connector section, select the Location of your data connector from the Multi-region field list.

11. In Your data connector name, enter a name for your data store.

12. Click Create. Gemini Enterprise creates your data store and displays your data stores on the Data Stores page.

    Note: By default, no tools or actions from your custom MCP servers are enabled. You must enable the tools or actions.

Step 3: Enable actions

After creating the custom MCP server data store, you must enable at least one tool or action before it can be used in Gemini Enterprise.

1. Go to your custom MCP server data store.

2. Open the Actions tab and select Reload custom actions to reauthenticate.

   Note: This action performs a tools/list call on the MCP server to retrieve available tools, which are then displayed on the screen.

3. Select the actions to enable.
4. Click Enable actions.

Step 4: Connect the MCP server data store to a Gemini Enterprise app

After creating the custom MCP server data store and enabling actions, you must connect the data store to a Gemini Enterprise app before it can be used.

1. In the Google Cloud console, go to the Gemini Enterprise page.
2. From the navigation menu, click Apps.
3. Select the Gemini Enterprise app where you want to connect your data store.
4. From the navigation menu of the app, click Connected data sources.
5. Click Add existing data stores and select your data store.
6. Click Connect.

Step 5: Query live JSON data with natural language

With the data store connected, Gemini Enterprise users can interact with live JSON services using natural language from the Gemini Enterprise web application. Each user authenticates with their own Connect AI credentials via the OAuth flow on first use.

1. Open Gemini Enterprise, click Connections and authorize CData Connect AI.
2. Ask natural language questions about your JSON services:
   • "Show me all JSON services from the last 30 days"
   • "What are the top records in JSON services by revenue?"
   • "List all active JSON services and their current status"
   • "Summarize JSON services activity for this quarter"
3. The agent automatically discovers available connections in Connect AI, identifies the most relevant JSON connection, generates SQL, and returns results — all without requiring the user to write queries or understand the underlying data structure.

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from Gemini Enterprise and other AI platforms, try CData Connect AI today!