Skip to content

MCP Server

The built-in MCP server of yunIO enables SAP data integration with AI platforms that support the Model Context Protocol. A typical use case is creating chatbots that query live SAP data.

Note

The MCP server is still in beta phase. This means, the MCP server is subject to change.

How It Works

By using the yunIO MCP endpoint, an AI agent / chatbot can execute yunIO web services to access real-time SAP data, such as customer master data or sales order information. This integration allows users to request and receive current SAP data in natural language while the system handles all connectivity and authorization tasks in the background.

Workflow

When a chatbot uses the yunIO MCP endpoint, the following process applies:

  1. A user sends a request to a chatbot, e.g., “Show all open sales orders."
  2. The chatbot identifies the user's intent to access SAP data.
  3. The chatbot calls yunIO's MCP endpoint at https://<hostname>.com:8177/mcp.
  4. The MCP server executes the corresponding yunIO service.
  5. yunIO connects to SAP, executes the request, and retrieves live data from SAP.
  6. The retrieved SAP data is returned to the chatbot platform via the MCP endpoint.
  7. The chatbot formats the response data and presents it to the user in text form.

Example

"Compare material 1379 with material 417 and represent the result in a diagram."

yunio-mcp-example

Setup in yunIO

To use yunIO's MCP server, configure yunIO as described below.

  • Create services in that access relevant SAP data that users are interested in.
  • When creating a service, activate the checkbox MCP enabled. This option exposes the service to the yunIO MCP server.
    mcp-service
  • Provide descriptive metadata for your services to ensure correct mapping between user intents and services.
    • Service Descriptions:
      Provide clear and meaningful service descriptions when creating a service. The MCP server uses this description to match user intents to the correct service. A precise description improves recognition accuracy and response quality.
    • Parameter Naming:
      Assign clear, self-explanatory names to all service parameters, e.g.,for input parameters in SAP transactions. Clear parameter names ensure consistent mapping between user input and service fields.
  • Expose the MCP endpoint of yunIO to the internet to make your services accessible to AI platforms:
    • Set up Transport Layer Security to ensure secured communication to the MCP server.
    • Enable the MCP endpoint in the Settings menu.
      mcp-settings
    • Open the MCP HTTPS port (default is 8177), e.g., using open port services.

Once the services and the MCP endpoint are set up, you can configure your chatbot / AI agent to consume the MCP endpoint.

Example Integration

Refer to the Knowledge Base Article: yunIO MCP Integration with Copilot for step-by-step instructions on how to integrate the yunIO MCP server with Microsoft Copilot.

Last update: November 19, 2025