MCP插件

Prerequisites

• Node.js: Version 18 or higher
• SAP CAP: Version 9 or higher
• Express: Version 5 or higher
• TypeScript: Optional but recommended

🚀 Quick Setup

Want to read the full documentation? Find it here

Step 1: Install the Plugin

npm install @gavdi/cap-mcp

The plugin follows CAP's standard plugin architecture and will automatically integrate with your CAP application upon installation.

The Setup

Your CAP service includes a workflow management system with MCP integration:

service WorkflowService {

  @mcp: {
    name       : 'get-my-pending-approval',
    description: 'Fetches workflows awaiting approval by the specified user',
    tool       : true
  }
  function getPendingApproval(userId: String) returns array of Workflows;
}

📝 Usage

🌟 Example AI Interactions

Once configured, AI agents can interact with your CAP data naturally; Let's take an example from the standard CAP Bookshop:

• "Show me the top 5 books with highest stock" → Queries Books resource with $orderby=stock desc&$top=5
• "Find authors whose names contain 'Smith'" → Uses $filter=contains(name,'Smith') on Authors resource
• "Get the current stock for book ID 123" → Calls the get-stock tool for the specified book
• "Give me a book recommendation" → Executes the book-recommendation tool

While this shows how this example CDS annotation works, the possibilities are endless and only you and your data sets the boundaries.

📋 Business Case Example: Workflow Approval Management

Step 2: Configure Your CAP Application

Add MCP configuration to your package.json:

{
  "cds": {
    "mcp": {
      "name": "my-bookshop-mcp",
      "auth": "inherit",
      "wrap_entities_to_actions": false,
      "wrap_entity_modes": ["query", "get"],
      "instructions": "MCP server instructions for agents"
    }
  }
}

🔧 Configuration

Plugin Configuration

Configure the MCP plugin through your CAP application's package.json or .cdsrc file:

{
  "cds": {
    "mcp": {
      "name": "my-mcp-server",
      "version": "1.0.0",
      "auth": "inherit",
      "instructions": "mcp server instructions for agents",
      "capabilities": {
        "resources": {
          "listChanged": true,
          "subscribe": false
        },
        "tools": {
          "listChanged": true
        },
        "prompts": {
          "listChanged": true
        }
      }
    }
  }
}

Configuration Options

Authentication Configuration

The plugin supports two authentication modes:

"inherit" Mode (Default)

Uses your CAP application's existing authentication system:

{
  "cds": {
    "mcp": {
      "auth": "inherit"
    },
    "requires": {
      "auth": {
        "kind": "xsuaa"
      }
    }
  }
}

"none" Mode (Development/Testing)

Disables authentication completely:

{
  "cds": {
    "mcp": {
      "auth": "none"
    }
  }
}

⚠️ Security Warning: Only use "none" mode in development environments. Never deploy to production without proper authentication.

Authentication Flow

1. MCP client connects to /mcp endpoint
2. If the authentication style used is OAuth, the OAuth flow will be executed
3. CAP authentication middleware validates credentials (if auth: "inherit")
4. MCP session established with authenticated user context
5. All MCP operations (resources, tools, prompts) inherit the authenticated user's permissions

Check if MCP endpoint is accessible

curl http://localhost:4004/mcp/health

CAP MCP Plugin - AI With Ease

This implementation is based on the Model Context Protocol (MCP) put forward by Anthropic. For more information on MCP, please have a look at their official documentation.

CAP-MCP Plugin

A CAP (Cloud Application Programming) plugin that automatically generates Model Context Protocol (MCP) servers from your CAP services using simple annotations. Transform your CAP OData services into AI-accessible resources, tools, and prompts with minimal configuration.

Test specific components

npm test -- --testPathPattern=annotations # Test annotation parsing npm test -- --testPathPattern=mcp # Test MCP functionality npm test -- --testPathPattern=security # Test security boundaries npm test -- --testPathPattern=auth # Test authentication

Or run integration tests

npm test -- --testPathPattern=integration ```

🔧 Troubleshooting