CBETA MCP Server

中文文档

MCP (Model Context Protocol) Server for CBETA Online - Chinese Buddhist Electronic Text Association.

CBETA contains over 100 million characters of Buddhist scriptures, including the Taishō Tripiṭaka, Xuzangjing, and many other collections.

Features

🔧 Tools

📚 Resources

• cbeta://catalog - Complete scripture catalog

💬 Prompts

• explain_sutra - Explain sutra passages
• buddhist_term - Look up Buddhist terminology

Installation

Option 1: Local (Node.js)

# Clone the repository
git clone https://github.com/your-username/cbeta-mcp.git
cd cbeta-mcp

# Install dependencies
npm install

# Build
npm run build

# Run
npm start

Option 2: Cloudflare Workers (Recommended)

Prerequisites

1. Cloudflare account
2. Node.js (v18+)
3. Wrangler CLI

Deployment Steps

# 1. Clone the repository
git clone https://github.com/your-username/cbeta-mcp.git
cd cbeta-mcp

# 2. Install dependencies
npm install

# 3. Login to Cloudflare
npx wrangler login

# 4. Deploy to Cloudflare Workers
npm run deploy

After deployment, your MCP server will be available at:

https://cbeta-mcp.<your-subdomain>.workers.dev

Local Development

# Start local development server
npm run dev:worker

# Test with MCP Inspector
npx @modelcontextprotocol/inspector@latest

Configuration

Claude Desktop

Add to your Claude Desktop config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

For Local Server

{
  "mcpServers": {
    "cbeta": {
      "command": "node",
      "args": ["C:\\path\\to\\cbeta-mcp\\dist\\index.js"]
    }
  }
}

For Cloudflare Workers

{
  "mcpServers": {
    "cbeta": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://cbeta-mcp.your-subdomain.workers.dev/sse"
      ]
    }
  }
}

Common Work IDs

API Reference

search_sutra

Search for Buddhist scriptures.

Parameters:

• query (required): Search keywords
• scope (optional): Search scope (T, X, N, etc.)
• page (optional): Page number (default: 1)
• limit (optional): Results per page (default: 10)

get_sutra_content

Get the content of a specific volume.

Parameters:

• work_id (required): Work ID (e.g., T0001)
• juan (optional): Volume number (default: 1)
• format (optional): Output format ("text" or "html")

browse_catalog

Browse the scripture catalog.

Parameters:

• catalog_id (optional): Catalog ID to browse

get_work_info

Get detailed information about a work.

Parameters:

• work_id (required): Work ID

Development

# Install dependencies
npm install

# Build local version
npm run build

# Build for Workers
npm run build:worker

# Run tests with MCP Inspector
npm run inspector

License

MIT

Credits

• CBETA - Chinese Buddhist Electronic Text Association
• DILA - Dharma Drum Institute of Liberal Arts