Gamma

MCP server for Gamma.app - AI-powered presentation, document, and website generation.

Features

• Generate from scratch - Create presentations, documents, social posts, or webpages from text
• Create from template - Adapt existing Gamma templates with new content
• List themes - Browse available themes for styling
• List folders - Browse workspace folders for organization
• Poll generation status - Check when async generation completes

Installation

npm install @purple-horizons/gamma-mcp

Or clone and build:

git clone https://github.com/Purple-Horizons/gamma-mcp.git
cd gamma-mcp
npm install
npm run build

Configuration

Environment Variable

Set your Gamma API key:

export GAMMA_API_KEY=sk-gamma-xxxxxxxx

Get your API key from Gamma Account Settings (requires Pro, Ultra, Teams, or Business plan).

Claude Desktop / OpenClaw

Add to your MCP config:

{
  "mcpServers": {
    "gamma": {
      "command": "node",
      "args": ["/path/to/gamma-mcp/dist/index.js"],
      "env": {
        "GAMMA_API_KEY": "sk-gamma-xxxxxxxx"
      }
    }
  }
}

mcporter

Add to ~/.config/mcporter/mcporter.json:

{
  "servers": {
    "gamma": {
      "command": "node",
      "args": ["/path/to/gamma-mcp/dist/index.js"],
      "env": {
        "GAMMA_API_KEY": "sk-gamma-xxxxxxxx"
      }
    }
  }
}

Tools

gamma_generate

Generate a new gamma from text input.

Parameters:

• inputText (required) - Content to generate from (text + image URLs)
• textMode (required) - generate | condense | preserve
• format - presentation | document | social | webpage
• themeId - Theme ID (from gamma_list_themes)
• numCards - Number of slides (1-60 for Pro, 1-75 for Ultra)
• cardSplit - auto | inputTextBreaks
• additionalInstructions - Extra generation guidance
• folderIds - Array of folder IDs to save to
• exportAs - pdf | pptx
• textAmount - brief | medium | detailed | extensive
• textTone - Tone description (e.g., "professional, inspiring")
• textAudience - Target audience
• textLanguage - Language code (default: "en")
• imageSource - aiGenerated | pictographic | pexels | giphy | webAllImages | webFreeToUse | webFreeToUseCommercially | placeholder | noImages
• imageModel - AI model for images (e.g., "flux-1-pro", "imagen-4-pro")
• imageStyle - Image style description
• dimensions - Card dimensions (format-dependent)

Returns: { generationId: "..." }

gamma_get_generation

Check generation status.

Parameters:

• generationId (required) - ID from gamma_generate

Returns:

{
  "status": "pending" | "completed",
  "generationId": "...",
  "gammaUrl": "https://gamma.app/docs/...",
  "credits": { "deducted": 150, "remaining": 3000 }
}

gamma_create_from_template

Create a gamma based on an existing template.

Parameters:

• gammaId (required) - Template gamma ID
• prompt (required) - Instructions and content
• themeId - Override theme
• folderIds - Destination folders
• exportAs - pdf | pptx
• imageModel - AI model for new images
• imageStyle - Style for new images

Returns: { generationId: "..." }

gamma_list_themes

List available themes.

Parameters:

• query - Search by name
• limit - Max results (default 50)
• after - Pagination cursor

Returns:

{
  "data": [{ "id": "...", "name": "...", "type": "standard|custom" }],
  "hasMore": false,
  "nextCursor": null
}

gamma_list_folders

List workspace folders.

Parameters:

• query - Search by name
• limit - Max results (default 50)
• after - Pagination cursor

Returns:

{
  "data": [{ "id": "...", "name": "..." }],
  "hasMore": false,
  "nextCursor": null
}

Usage Example

// 1. Generate a presentation
const gen = await gamma_generate({
  inputText: "5 ways AI is transforming healthcare",
  textMode: "generate",
  format: "presentation",
  numCards: 10,
  imageSource: "aiGenerated",
  imageStyle: "modern, professional photography"
});

// 2. Poll for completion
let status;
do {
  await sleep(5000);
  status = await gamma_get_generation({ generationId: gen.generationId });
} while (status.status === "pending");

// 3. Use the result
console.log(status.gammaUrl); // https://gamma.app/docs/xxxxx

Credits

Gamma uses a credit-based system:

• ~3-4 credits per card
• ~2-120 credits per image (depends on model)

Check your remaining credits in the generation response.

License

MIT