Auto PPT Generator Agent

Auto PPT Generator Agent

Enables AI-powered generation of PowerPoint presentations with dynamic content, themes, and tones. Supports custom topics, audience, and slide count via the generate_ppt tool.

Category
访问服务器

README

Automatic PPT Generator Agent (MCP + VS Code)

A beginner-friendly, end-to-end project that builds:

  • An MCP server (Model Context Protocol) that can generate PowerPoint files
  • A Node.js API backend
  • A professional, interactive web UI
  • Dynamic slide content that changes on every generation

What You Will Build

  • MCP server: exposes a generate_ppt tool
  • Backend API: validates requests, calls generation pipeline, serves generated files
  • Presentation engine: creates slide deck structure, design themes, and content variants
  • Interactive UI: enter topic, audience, tone, style, and generate/download PPT

1) Prerequisites

Install these first:

  1. Node.js 20+ (recommended LTS)
  2. VS Code
  3. npm (comes with Node.js)
  4. Groq API key for AI-generated content
  5. Internet access for live data lookup

Check versions in terminal:

node -v
npm -v

2) Project Setup

From this project folder:

npm install
npm run dev

The app starts at:

  • UI: http://localhost:5173
  • API: http://localhost:8787

3) Environment Variables

Copy .env.example to .env and update values:

Copy-Item .env.example .env

Important variables:

  • PORT: backend port
  • VITE_API_BASE_URL: frontend API URL
  • PPT_PROVIDER: set to groq
  • GROQ_API_KEY: optional, required only when using Groq
  • GROQ_MODEL: optional, default is llama-3.1-70b-versatile

Set GROQ_API_KEY in .env to enable AI-written slide content. The deck content is built from live web data first, using Wikipedia + GDELT signals, and then shaped into slides by Groq.

In MCP config, set the same Groq variables under env.

Security note: if a real key was ever pasted into a shared/example file, rotate it in your provider dashboard and replace it with a placeholder.


4) How Dynamic Content Works

Every generation changes because the app combines:

  1. Live topic lookup from Wikipedia and current news signals
  2. Topic-family slide blueprints that change by subject area
  3. Variable slide structures and slide kinds
  4. Rotating content angles and examples
  5. Timestamp/seed-based variation
  6. Groq-generated slide copy on top of live data

This ensures different wording and structure each run, while also grounding the output in current information.


5) How MCP Fits In

This project includes a local MCP server:

  • File: mcp/server.js
  • Tool exposed: generate_ppt

You can connect this MCP server from compatible MCP clients (including VS Code flows) so agent workflows can trigger PPT generation.

MCP Tool Input

{
  "topic": "AI in Healthcare",
  "audience": "college students",
  "tone": "engaging",
  "slides": 8,
  "theme": "corporate"
}

MCP Tool Output

{
  "ok": true,
  "fileName": "ai-in-healthcare-2026-06-19T10-00-00-000Z.pptx",
  "downloadUrl": "/generated/ai-in-healthcare-2026-06-19T10-00-00-000Z.pptx"
}

6) Beginner-Friendly Workflow in VS Code

  1. Open this folder in VS Code.
  2. Open terminal.
  3. Run npm install.
  4. Run npm run dev.
  5. Open http://localhost:5173.
  6. Enter topic and options.
  7. Click Generate PPT.
  8. Download the file.

7) Production Build

npm run build
npm run start

8) Extend the Agent

Ideas:

  1. Add charts from real data sources
  2. Add image search integration
  3. Add brand kit upload (logo/colors/fonts)
  4. Add multilingual slide generation
  5. Add speaker notes auto-generation

9) Troubleshooting

Error: Cannot find module

Run:

npm install

UI opens but generate fails

  • Check backend running on 8787
  • Check .env values
  • Check terminal logs

LLM not used

  • Set GROQ_API_KEY in .env
  • Restart npm run dev

10) File Structure

See project layout in this repository:

  • src/server/ backend + generation pipeline
  • src/client/ modern interactive frontend
  • mcp/ MCP server entrypoint
  • generated/ exported PowerPoint files

You can now use this as a foundation to build a strong custom PPT generation agent.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选