MultiAgent PPT
MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Protocol）+ ADK（Agent Development Kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制
What is MultiAgent PPT?
MultiAgent PPT is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to multiagentppt 是一个集成了 a2a（agent2agent）+ mcp（model context protocol）+ adk（agent development kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制
MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Protocol）+ ADK（Agent Development Kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Pro
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx multiagentpptConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MultiAgent PPT
MultiAgentPPT is a self-hosted AI system that generates professional PowerPoint presentations through a coordinated network of specialized agents using the A2A (Agent2Agent), MCP (Model Context Protocol), and ADK (Agent Development Kit) architectures. Users provide a research topic and the system autonomously drafts an outline, researches each section in parallel, and assembles slides with streaming real-time feedback. It is designed for researchers, educators, and business analysts who need to turn complex topics into structured presentations quickly.
Prerequisites
- Python 3.12 and conda (Miniconda or Anaconda) installed
- Node.js 18+ and pnpm installed for the frontend
- Docker installed and running (for the PostgreSQL database)
- API keys for the LLM provider you intend to use (e.g. OpenAI, Anthropic)
- An MCP-compatible client or the bundled web frontend
Clone the repository
Clone the MultiAgentPPT repository and enter the project directory.
git clone https://github.com/johnson7788/MultiAgentPPT.git
cd MultiAgentPPTStart the PostgreSQL database via Docker
Launch a PostgreSQL container that the frontend uses to persist presentations.
docker run --name postgresdb -p 5432:5432 \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=welcome \
-d postgresSet up and start the Python backend
Create a conda environment, install backend dependencies, and configure the .env files for each agent module with your LLM API keys.
conda create --name multiagent python=3.12
conda activate multiagent
cd backend
pip install -r requirements.txt
# Copy and edit .env files for each module:
# backend/simpleOutline/.env, backend/simplePPT/.env,
# backend/slide_outline/.env, backend/slide_agent/.envConfigure and start the Next.js frontend
Install frontend dependencies, configure the .env file with the database URL and agent URLs, push the database schema, and start the development server.
cd ../frontend
cp env_template .env
# Edit .env:
# DATABASE_URL="postgresql://postgres:welcome@localhost:5432/presentation_ai"
# A2A_AGENT_OUTLINE_URL="http://localhost:10001"
# A2A_AGENT_SLIDES_URL="http://localhost:10011"
# DOWNLOAD_SLIDES_URL="http://localhost:10021"
pnpm install
pnpm db:push
npm run devGenerate a presentation
Open http://localhost:3000/presentation in your browser, enter a research topic, and the multi-agent pipeline will generate and stream the slides back to you.
MultiAgent PPT Examples
Client configuration
Frontend environment file showing how to connect the web UI to each backend agent service.
{
"mcpServers": {
"multiagentppt": {
"command": "python",
"args": ["-m", "slide_agent"],
"env": {
"DATABASE_URL": "postgresql://postgres:welcome@localhost:5432/presentation_ai",
"A2A_AGENT_OUTLINE_URL": "http://localhost:10001",
"A2A_AGENT_SLIDES_URL": "http://localhost:10011",
"DOWNLOAD_SLIDES_URL": "http://localhost:10021"
}
}
}
}Prompts to try
Example topics to generate presentations about using the MultiAgentPPT web interface.
- "Generate a 10-slide presentation on the history and future of electric vehicles"
- "Create a business proposal deck for a SaaS product targeting SMBs"
- "Build a research summary presentation on CRISPR gene editing advances in 2024"
- "Generate a slide deck comparing microservices and monolith architectures"Troubleshooting MultiAgent PPT
Frontend cannot connect to PostgreSQL — connection refused error
Ensure the Docker container is running with `docker ps`. Check that DATABASE_URL in frontend/.env uses the correct host (localhost) and port (5432) and that `pnpm db:push` was run after starting the database.
Backend agents fail to start or crash immediately
Each backend module (simpleOutline, simplePPT, slide_outline, slide_agent) needs its own .env file with valid LLM API credentials. Copy the template files and fill in your API keys before starting the services.
Presentation generation hangs indefinitely
Verify that all four agent services are running and listening on their configured ports (10001, 10011, 10021). Check the backend console output for errors related to LLM API rate limits or invalid API keys.
Frequently Asked Questions about MultiAgent PPT
What is MultiAgent PPT?
MultiAgent PPT is a Model Context Protocol (MCP) server that multiagentppt 是一个集成了 a2a（agent2agent）+ mcp（model context protocol）+ adk（agent development kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MultiAgent PPT?
Follow the installation instructions on the MultiAgent PPT GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MultiAgent PPT?
MultiAgent PPT works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MultiAgent PPT free to use?
Yes, MultiAgent PPT is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MultiAgent PPT Alternatives — Similar Business Applications Servers
Looking for alternatives to MultiAgent PPT? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MultiAgent PPT in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MultiAgent PPT?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.