MCP Presentations
Remote MCP server running on Cloudflare Workers that creates PowerPoint presentations with customizable slides, layouts, and bullet points, along with basic calculator functions.
README
MCP Presentations - Remote MCP Server with PowerPoint Creation
This MCP server runs on Cloudflare Workers and provides five tools:
- ✅ add - Simple addition calculator
- ✅ calculate - Multi-operation calculator (add, subtract, multiply, divide)
- ✅ create_presentation - Creates PowerPoint presentations and stores them in R2
- ✅ get_presentation_url - Retrieves download URL for stored presentations
- ✅ list_presentations - Lists all stored presentations with metadata
Architecture
This project uses:
- Main Worker (TypeScript) - MCP server that handles tool requests
- R2 Storage - Cloudflare R2 bucket with public access for storing generated presentations
Generated presentations are automatically stored in R2 with metadata and can be accessed directly via public R2 URLs, leveraging Cloudflare's global CDN for fast downloads.
Get started:
This will deploy your MCP server to a URL like: remote-mcp-server-authless.<your-account>.workers.dev/sse
Alternatively, you can use the command line below to get the remote MCP Server created on your local machine:
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
🚀 Quick Deployment
Prerequisites: Create R2 bucket first (if not already created)
wrangler r2 bucket create mcp-presentations
Deploy the worker:
wrangler deploy
Before deploying to production, update WORKER_URL in wrangler.jsonc to your production URL.
See DEPLOYMENT.md and R2-STORAGE.md for detailed instructions.
🎨 Using the PowerPoint Tool
The create_presentation tool creates presentations and stores them in R2:
- title: Presentation filename
- slides: Array of slide objects with layout, title, and bullets
Example:
{
"title": "My Presentation",
"slides": [
{
"layout": "title",
"title": "Welcome"
},
{
"layout": "title_and_content",
"title": "Key Points",
"bullets": ["Point 1", "Point 2", "Point 3"]
}
]
}
Returns: Download URL and metadata
Additional Tools
Get presentation URL:
{ "filename": "My_Presentation_1732567890123.pptx" }
List all presentations:
{ "limit": 10 }
See R2-STORAGE.md for complete R2 storage documentation.
Customizing your MCP Server
To add your own tools to the MCP server, define each tool inside the init() method of src/index.ts using this.server.tool(...).
Connect to Cloudflare AI Playground
You can connect to your MCP server from the Cloudflare AI Playground, which is a remote MCP client:
- Go to https://playground.ai.cloudflare.com/
- Enter your deployed MCP server URL (
remote-mcp-server-authless.<your-account>.workers.dev/sse) - You can now use your MCP tools directly from the playground!
Connect Claude Desktop to your MCP server
You can also connect to your remote MCP server from local MCP clients, by using the mcp-remote proxy.
To connect to your MCP server from Claude Desktop, follow Anthropic's Quickstart and within Claude Desktop go to Settings > Developer > Edit Config.
Update with this configuration:
{
"mcpServers": {
"calculator": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/sse" // or remote-mcp-server-authless.your-account.workers.dev/sse
]
}
}
}
Restart Claude and you should see the tools become available.
📚 Documentation
📖 Complete Documentation Index - Find any documentation quickly!
Quick Access
- R2-STORAGE.md - R2 storage configuration and usage guide
- QUICKREF.md - Quick reference card with common commands
- DEPLOYMENT.md - Detailed deployment guide (step-by-step)
- EXAMPLES.md - PowerPoint usage examples and AI prompts
- IMPLEMENTATION.md - Technical architecture details
- SUMMARY.md - Complete project overview
- ARCHITECTURE.md - System architecture and diagrams
- TESTING.md - Comprehensive testing guide
- CHANGELOG.md - Version history and roadmap
🛠️ Helper Scripts
deploy.ps1- One-command deployment for both workersdev.ps1- Instructions for local development setup
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。