Integrate Live Sage X3 Cloud Data in the Windsurf IDE via CData Connect AI

Windsurf is an AI-native IDE built around Cascade, an autonomous coding agent that understands project context and executes multi-step tasks directly inside the editor. Cascade supports the Model Context Protocol (MCP), allowing the agent to discover and call external tools and data sources without leaving the development environment.

By integrating Windsurf with CData Connect AI through the built-in MCP server, the Cascade agent gains governed, real-time access to live Sage X3 Cloud data. This enables developers to list catalogs, inspect schemas, and query records from Sage X3 Cloud data within the IDE using natural language prompts.

This article explains how to configure Sage X3 Cloud connectivity in Connect AI, generate the required personal access token, configure the Connect AI MCP Server in Windsurf, and verify the integration by querying live Sage X3 Cloud data from the Cascade chat.

Step 1: Configure Sage X3 Cloud connectivity for Windsurf

Connectivity to Sage X3 Cloud from Windsurf is made possible through Connect AI's Remote MCP Server. To interact with Sage X3 Cloud data from Windsurf, start by creating and configuring a Sage X3 Cloud connection in Connect AI.

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

2. Select Sage X3 Cloud from the Add Connection panel

3. Enter the necessary authentication properties to connect to Sage X3 Cloud.

   Sage X3 Cloud uses the OAuth 2.0 Client Credentials flow, and an X-API-Key is also required for API access. Set AuthScheme to OAuth and specify the following connection properties:

   • URL: The base URL of your Sage X3 Cloud instance.
   • OAuthAccessTokenUrl: The OAuth token endpoint (e.g., https://your-auth-domain/oauth/token).
   • OAuthClientId: Your OAuth application client ID.
   • OAuthClientSecret: Your OAuth application client secret.
   • Audience: The API audience value for the token request.
   • XAPIKey: The X-API-Key provided by your Sage X3 Cloud administrator.
   • Folder: The Sage X3 folder name (e.g., SEED). This folder is used as the default schema.
   • Folders (optional): A comma-separated list of Sage X3 folders (e.g., SEED,PERF). Each folder is exposed as a separate schema, so you can query across folders with the Schema.Table syntax.

   The driver obtains an access token with the Client Credentials flow and sends it with the X-API-Key on every API request. With InitiateOAuth set to GETANDREFRESH (the default), the driver acquires and refreshes the token automatically.

   
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 Windsurf. 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 Sage X3 Cloud connection configured and a PAT generated, Windsurf can now connect to Sage X3 Cloud data.

Step 2: Configure Connect AI MCP in Windsurf

Next, configure the Connect AI Remote MCP Server in Windsurf so that the Cascade agent can discover and call live data tools through Connect AI.

1. Download and install the Windsurf IDE
2. Open Windsurf, click your profile icon in the top right, and select Windsurf Settings
3. Under the Cascade section, locate MCP Servers and click Open MCP Registry
4. In the MCP Marketplace, click Add custom MCP in the top right
5. This opens the mcp_config.json file. Paste the following JSON:

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

   Note: Windsurf will use Basic authentication with Connect AI. Combine your Connect AI user email and the PAT you created earlier in the format email:PAT, base64 encode the combined string, and prefix it with Basic. For example, given [email protected]:ABC123...XYZ789, the Authorization header value becomes something like: Basic dXNlckBkb21haW4uY29tOkFCQzEyMy4uLlhZWjc4OQ==

   
6. Save the mcp_config.json file and return to the MCP Registry
7. Under Installed, confirm that cdata-mcp is listed and marked as Enabled

With the MCP server registered and enabled, Windsurf is ready to query live Sage X3 Cloud data through Connect AI.

Step 3: Query live Sage X3 Cloud data from Windsurf

With the integration complete, use the Cascade chat panel in Windsurf to interact with live Sage X3 Cloud data through natural language prompts.

1. On the top bar of Windsurf, switch from Editor to Agent to open a new Cascade chat
2. At the bottom of the chat panel, confirm that the cdata-mcp server is listed and the toggle is enabled
3. Start interacting with the agent by entering prompts like:
   • List all catalogs in my cdata-mcp connection
   • Show the available schemas and tables for Sage X3 Cloud
   • Query the top 5 records from a table in Sage X3 Cloud data
4. The Cascade agent calls the Connect AI MCP Server and returns live results from Sage X3 Cloud data

At this point, your Windsurf IDE communicates with the Connect AI MCP Server and retrieves live Sage X3 Cloud data through remote MCP directly from the editor.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today! Download a free 14-day trial of CData Connect AI today, and as always, our Support Team is available to assist you with any questions you may have.