SAP Business One

Exposes SAP Business One Service Layer actions to Microsoft Copilot Studio via MCP streamable protocol for connecting, status checks, and Sales Order creation.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "nxr10-mcp-sap": {
      "command": "python",
      "args": [
        "server.py"
      ],
      "env": {
        "SAP_BASE_URL": "https://your-sap-server:50000/b1s/v2",
        "SAP_PASSWORD": "your_password",
        "SAP_USERNAME": "your_user",
        "SAP_COMPANY_DB": "YOUR_DB"
      }
    }
  }
}

You set up an MCP (Model Context Protocol) server to expose SAP Business One Service Layer functionality to Microsoft Copilot Studio. This enables represented actions like connecting to SAP, checking status, and creating Sales Orders through a streamable MCP interface, so Copilot Studio can call them as custom actions.

How to use

You interact with the SAP Business One MCP Server by first connecting to SAP Business One, then using the exposed actions to perform tasks. The core tools you’ll use are sap_connect to establish a connection, sap_status to verify the connection health, and sap_create_sales_order to create a Sales Order with full validation. Use Copilot Studio’s custom connector to access these tools as actions, so a conversational workflow can drive SAP operations.

Typical workflows include establishing a connection to SAP, validating the connection, and then creating transactional records such as Sales Orders. You will receive structured results from the server indicating success or failure, including key identifiers like DocEntry and DocNum for created records.

How to install

Prerequisites: Python 3.11 or later, and SAP Business One with the Service Layer enabled. Ensure environment variables for SAP access are prepared before starting the server.

Step-by-step commands you run locally:

cp .env.example .env

# Edit .env to set SAP access
# SAP_BASE_URL=https://your-sap-server:50000/b1s/v2
# SAP_COMPANY_DB=YOUR_DB
# SAP_USERNAME=your_user
# SAP_PASSWORD=your_password

pip install -r requirements.txt

# Start the MCP server
python server.py

Configuration and deployment notes

Environment variables control how the server connects to SAP Business One. You should configure these in the .env file and ensure they are supplied to your deployment environment as needed.

For deployment in Azure Container Apps, you will typically provision the container with the same environment variables available as secrets and set the host for Copilot Studio integration to the public endpoint of your container app.

Health and troubleshooting

Check server health with the built-in health endpoint as part of your validation workflow. If you encounter connectivity issues, verify that SAP_BASE_URL, SAP_USERNAME, SAP_PASSWORD, and SAP_COMPANY_DB are correct and that network connectivity to the SAP Service Layer is available.

Common operational tips include validating that the SAP Service Layer is reachable from the MCP server host and ensuring that credentials used by the server are kept secure, ideally stored as secrets in your container or cloud environment.

Example usage concepts (high level)

After you configure Copilot Studio with a custom connector that points to the MCP schema, you will be able to trigger actions such as sap_connect, sap_status, and sap_create_sales_order from your conversational flows. The server returns structured results that include an indicator of success and key documentation identifiers when appropriate.

Available tools

sap_connect

Connect to SAP Business One Service Layer and initialize the MCP session.

sap_status

Check the current connection status to SAP Business One.

sap_create_sales_order

Create a Sales Order in SAP Business One with full validation via the MCP interface.

Built by

VeilStrat

AI signals for GTM teams