Sap MCP

🚀 SAP MCP Server and Client

This project offers an MCP (Model Context Protocol) server and client implementation for interacting with SAP systems via a RESTful API. It simplifies the process of making SAP function calls and provides a clear structure for configuration, usage, and extension.

🚀 Quick Start

To quickly get started with this project, follow these steps:

1. Install the required dependencies.
2. Configure the config.json file.
3. Run the client or server as needed.

✨ Features

• RESTful API Interaction: Communicate with SAP systems using a RESTful API.
• Function Call Tool: The call_sap_function tool simplifies SAP function calls.
• Multiple Modes: Support for running the server in different modes (e.g., HTTP).
• Error Handling: Basic error handling for common issues.

📦 Installation

Install the required dependencies (MCP SDK version 1.3.0 or higher):

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

Running the Client

To run the client example:

python sap_client.py

This will:

1. Start the MCP server.
2. Connect to it via stdio.
3. Execute example SAP function calls.
4. Display the results.

Running the Server in HTTP Mode

To run the server in HTTP mode:

python sap_server.py --transport http --host 127.0.0.1 --port 8000

Testing with HTTP Client

To test with the HTTP client:

python simple_test.py

Advanced Usage

Using the MCP Tool Directly

The MCP server provides a call_sap_function tool with the following parameters:

• function_name (string, required): Name of the SAP function to call.
• parameters (object, optional): Parameters for the SAP function.

Example tool call:

{
  "function_name": "BAPI_GL_GETGLACCPERIODBALANCES",
  "parameters": {
    "COMPANYCODE": "C999",
    "GLACCT": "0010010101",
    "FISCALYEAR": "2023",
    "CURRENCYTYPE": "10"
  }
}

📚 Documentation

Project Structure

• config.json: Configuration file for SAP API connection.
• sap_server.py: MCP server implementation with SAP function calling tool.
• sap_client.py: MCP client demonstrating usage of the server.
• requirements.txt: Python dependencies.
• test_mcp_client_final.py: HTTP-based MCP client test.
• simple_test.py: Simple HTTP test for the MCP server.

Configuration

Update the config.json file with your SAP API connection details:

{
  "sap_api": {
    "base_url": "http://192.168.1.129:8000/zmy_service",
    "client": "100",
    "username": "your_username",
    "password": "your_password"
  }
}

If you don't need authentication, you can leave the username and password fields as they are or remove them entirely.

How It Works

1. The MCP server (sap_server.py) provides a tool called call_sap_function.
2. When called, this tool makes an HTTP POST request to your SAP RESTful API.
3. The API response is returned through the MCP protocol to the client.
4. The client (sap_client.py) demonstrates how to use this tool with example calls.

Extending the Implementation

To add more SAP functions or modify the behavior:

1. Modify the call_sap_tool function in sap_server.py.
2. Add additional examples in sap_client.py.
3. Update the configuration in config.json as needed.

Error Handling

The implementation includes basic error handling for:

• Network errors.
• JSON parsing errors.
• Missing function names. Errors are returned in the response as JSON objects with an "error" key.

Additional Notes

For SAP dynamic RFC code, please contact: zhangxj1@foxmail.com