Majin Slide

Generates AI-powered markdown slide prompts and saves them as Markdown files for professional presentations.

javascript

18

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "nanameru-majin-slide-mcp": {
      "command": "npx",
      "args": [
        "@taiyokimura/majin-slide-mcp@latest"
      ]
    }
  }
}

This/Majin Slide MCP is a server that generates structured prompts for AI-assisted markdown slide creation and saves the results as Markdown files. It helps you produce polished, presentation-ready prompts and templates that you can feed to any compatible AI model.

How to use

You interact with the Majin Slide MCP through your MCP client. Start the server locally or connect to it via your chosen client to generate slide prompts and save them as Markdown. Use the provided tools to create a comprehensive slide prompt from your topic, then apply your preferred AI to draft the actual slide content. Finally, save the output as a Markdown file and convert it with your preferred presentation tool.

How to install

Prerequisites: you need Node.js 18 or newer and an MCP client such as VS Code, Cursor, Windsurf, Claude Desktop, or another MCP client.

{
  "mcpServers": {
    "majin-slide": {
      "command": "npx",
      "args": ["@taiyokimura/majin-slide-mcp@latest"]
    }
  }
}

Additional sections

Configuration and usage details are embedded directly in the steps below to ensure you can set up and run the server without additional references.

Available tools

generate_slide_prompt

Generates a comprehensive Marp-oriented prompt based on a specified topic, embedding it into a prompt tailored for AI slide creation.

create_slide_file

Saves the generated slide content to a markdown file with a specified filename and content, optionally in a chosen output directory.