Integrate Trae with Live SAP Ariba Procurement Data via CData Connect AI
Trae is an AI-powered integrated development environment (IDE) that pairs a familiar editor with agent modes such as Builder and SOLO. It supports the Model Context Protocol (MCP), so you can add external tools and data sources and give the agent access to live data.
By integrating Trae with CData Connect AI through the built-in MCP Server, Trae gains governed, real-time access to live SAP Ariba Procurement data. You can list catalogs, explore schemas, and query records from SAP Ariba Procurement data using natural language prompts, with all data access running securely against authorized sources.
This article explains how to configure SAP Ariba Procurement connectivity in Connect AI, generate the required personal access token, install Trae, add the Connect AI MCP Server, configure an LLM model, and verify the integration by querying live SAP Ariba Procurement data from the Trae agent.
Step 1: Configure SAP Ariba Procurement connectivity for Trae
Connectivity to SAP Ariba Procurement from Trae is made possible through Connect AI's Remote MCP Server. To interact with SAP Ariba Procurement data from Trae, start by creating and configuring a SAP Ariba Procurement connection in Connect AI.
- Log into Connect AI, click Sources, and then click Add Connection
- Select SAP Ariba Procurement from the Add Connection panel
-
Enter the necessary authentication properties to connect to SAP Ariba Procurement.
In order to connect with SAP Ariba Procurement, set the following:
- ANID: Your Ariba Network ID.
- ANID: Specify which API you would like the provider to retrieve SAP Ariba data from. Select the Buyer or Supplier API based on your business role (possible values are PurchaseOrdersBuyerAPIV1 or PurchaseOrdersSupplierAPIV1).
- Environment: Indicate whether you are connecting to a test or production environment (possible values are TEST or PRODUCTION).
Authenticating with OAuth
After setting connection properties, you need to configure OAuth connectivity to authenticate.
- Set AuthScheme to OAuthClient.
- Register an application with the service to obtain the APIKey, OAuthClientId and OAuthClientSecret.
For more information on creating an OAuth application, refer to the Help documentation.
Automatic OAuth
After setting the following, you are ready to connect:
-
APIKey: The Application key in your app settings.
OAuthClientId: The OAuth Client Id in your app settings.
OAuthClientSecret: The OAuth Secret in your app settings.
When you connect, the provider automatically completes the OAuth process:
- The provider obtains an access token from SAP Ariba and uses it to request data.
- The provider refreshes the access token automatically when it expires.
- The OAuth values are saved in memory relative to the location specified in OAuthSettingsLocation.
- Click Save & Test
- 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 Trae. It is best practice to create a separate PAT for each integration to maintain granular access control.
- Click the gear icon () at the top right of the Connect AI app to open Settings
- On the Settings page, go to the Access Tokens section and click Create PAT
- Give the PAT a descriptive name and click Create
- Copy the token when displayed and store it securely. It will not be shown again
With the SAP Ariba Procurement connection configured and a PAT generated, Trae can now connect to SAP Ariba Procurement data through Connect AI.
Step 2: Install Trae and configure the Connect AI MCP Server
Next, install Trae, add the Connect AI Remote MCP Server, and configure an LLM model so the agent can discover and call live data tools through Connect AI.
- Download and install the Trae IDE, then launch the application
-
Switch to SOLO mode using the toggle at the top left, or press Ctrl + Alt + \
-
Click Toggle AI Sidebar to open the chat panel
-
Open Settings, then select MCP from the left menu
-
Click Add Manually
-
In the Configure Manually dialog, paste the following configuration and click Confirm:
{ "mcpServers": { "cdata-connect-ai": { "type": "streamable-http", "url": "https://mcp.cloud.cdata.com/mcp", "headers": { "Authorization": "Basic your_base64_encoded_email_PAT" } } } }Note: Trae 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==
Configure an LLM model
Trae requires at least one LLM model to power the agent's reasoning. Add a model so the agent can interpret prompts and call MCP tools through Connect AI.
- Return to Settings and select Models
-
Click Add Model, choose a provider such as OpenAI, Anthropic, or Google, select a model, enter your API key, and click Add Model
With the MCP server added and an LLM model configured, Trae is ready to query live SAP Ariba Procurement data through Connect AI.
Step 3: Query live SAP Ariba Procurement data from Trae
With the integration complete, use the Trae agent to interact with live SAP Ariba Procurement data through natural language prompts handled by the configured LLM.
-
In the chat panel, type @ and select Builder with MCP. Confirm that cdata-connect-ai is listed under Tools - MCP
-
Enter a prompt to interact with your data, for example:
- List all catalogs in cdata-connect-ai
- Show the available schemas and tables for SAP Ariba Procurement
- Query the top 5 records from a table in SAP Ariba Procurement data
-
Trae calls the Connect AI MCP Server and returns live results from SAP Ariba Procurement data
At this point, the Trae agent communicates with the Connect AI MCP Server and retrieves live SAP Ariba Procurement data through remote MCP tools directly from the IDE.
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, and our Support Team is available to help with any questions you have.