返回 MCP 目录
public公开dns本地运行

hana-mcp服务器

通过模型上下文协议,启用 SAP HANA Cloud 数据库与 Cursor IDE 之间的集成,提供用于管理机器学习模型和执行上下文的标准接口。

article

README

HANA Cloud MCP Server

A Model Context Protocol (MCP) server implementation for SAP HANA Cloud DB integration with Cursor IDE.

Overview

This server implements the Model Context Protocol (MCP) pattern for machine learning operations with SAP HANA Cloud. The MCP server provides a standardized interface for managing ML models, execution contexts, and communication protocols between applications and the HANA Cloud database.

Key features:

  • Model Registry: Central repository for model metadata and versioning
  • Context Management: Configure execution environments for models
  • Protocol Adapters: Standardized communication between models and applications
  • HANA Cloud Integration: Optimized for SAP HANA Cloud Database
  • Cursor IDE Support: Seamless integration with Cursor IDE

Architecture

The MCP server is built on a three-layer architecture:

  1. Model Layer: Manages model definitions, versions, and metadata
  2. Context Layer: Configures execution environments and runtime parameters
  3. Protocol Layer: Handles communication between applications and models
┌───────────────────────────────────────────────────────┐
│                   CLIENT APPLICATIONS                  │
└───────────────────────────▲───────────────────────────┘
                            │
                            │ REST API
                            │
┌───────────────────────────▼───────────────────────────┐
│                       MCP SERVER                       │
│                                                       │
│  ┌─────────────┐    ┌─────────────┐    ┌─────────────┐ │
│  │  MODEL API  │    │ CONTEXT API │    │PROTOCOL API │ │
│  └──────┬──────┘    └──────┬──────┘    └──────┬──────┘ │
│         │                  │                  │        │
│  ┌──────▼──────┐    ┌──────▼──────┐    ┌──────▼──────┐ │
│  │    MODEL    │    │   CONTEXT   │    │  PROTOCOL   │ │
│  │   MANAGER   │    │   MANAGER   │    │   MANAGER   │ │
│  └──────┬──────┘    └──────┬──────┘    └──────┬──────┘ │
│         │                  │                  │        │
└─────────┼──────────────────┼──────────────────┼────────┘
          │                  │                  │
┌─────────▼──────────────────▼──────────────────▼────────┐
│                     HANA CLOUD DB                       │
└───────────────────────────────────────────────────────┘

Prerequisites

  • Python 3.8+
  • SAP HANA Cloud Database
  • Flask
  • HDBCLI (SAP HANA Client for Python)
  • Pandas

Installation

  1. Clone the repository:

    git clone https://github.com/yourusername/hana-mcp-server.git
    cd hana-mcp-server
    
  2. Create a virtual environment and install dependencies:

    python -m venv venv
    source venv/bin/activate  # On Windows: venvScriptsactivate
    pip install -r requirements.txt
    
  3. Run the setup script:

    python setup.py
    

    Follow the prompts to configure your HANA Cloud connection and server settings.

Configuration

The server uses environment variables for configuration. These can be set in a .env file:

# HANA Cloud Connection
HANA_HOST=your-hana-host.hanacloud.ondemand.com
HANA_PORT=443
HANA_USER=DBADMIN
HANA_PASSWORD=
help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端