Gamma MCP Server
Enables AI-powered generation of presentations, documents, and webpages through the Gamma API. Supports theme selection, folder management, and automatic export to PowerPoint or PDF formats.
README
Gamma MCP Server
A Model Context Protocol (MCP) server for Gamma AI that provides tools and resources for generating presentations, documents, and webpages using the Gamma Public API.
Features
Resources (2)
gamma://folders- List all folders (channels) in your Gamma workspacegamma://themes- List all available themes for generation
Tools (1)
generate_gamma- Generate Gamma content with AI, including automatic polling until completion
Prerequisites
- Node.js 18+
- Yarn package manager
- A Gamma API key (get one here)
Installation
-
Install dependencies:
yarn install -
Configure your API key:
Edit
src/gamma-api.service.tsand replace the placeholder API key:const GAMMA_API_KEY = 'sk-gamma-your-api-key-here';Replace
'sk-gamma-your-api-key-here'with your actual Gamma API key. -
Build the project:
yarn build
Running the Server
Development mode (with auto-reload):
yarn dev
Production mode:
yarn start
The server will start on http://localhost:3000 using streamable HTTP transport.
Connecting to Claude Desktop
To use this MCP server with Claude Desktop, add it to your Claude configuration:
macOS/Linux:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"gamma": {
"command": "node",
"args": ["/absolute/path/to/gamma-mcp-server/dist/index.js"]
}
}
}
Windows:
Edit %APPDATA%\Claude\claude_desktop_config.json with similar configuration.
Important: Replace /absolute/path/to/gamma-mcp-server with the actual absolute path to this project directory.
Usage Examples
Once connected to Claude Desktop, you can use natural language to interact with Gamma:
List Available Themes
Show me all available Gamma themes
List Workspace Folders
What folders do I have in my Gamma workspace?
Generate a Presentation
Create a 10-slide presentation about renewable energy using the "Modern Professional" theme
Generate with Export
Generate a presentation about AI trends and export it as a PowerPoint file
API Reference
Resources
gamma://folders
Returns all workspace folders with pagination automatically handled.
Response:
{
"folders": [
{"id": "fold_123", "name": "Marketing"},
{"id": "fold_456", "name": "Sales"}
],
"total": 2
}
gamma://themes
Returns all available themes with pagination automatically handled.
Response:
{
"themes": [
{
"id": "theme_123",
"name": "Modern Professional",
"type": "standard",
"colorKeywords": ["blue", "corporate"],
"toneKeywords": ["professional", "clean"]
}
],
"total": 50
}
Tools
generate_gamma
Generate Gamma content with automatic polling until completion.
Parameters:
inputText(required): Content to generate from (max 400k chars)textMode(required):"generate","condense", or"preserve"format(optional):"presentation","document","social", or"webpage"(default: "presentation")numCards(optional): Number of cards/pages to generatethemeId(optional): Theme ID from the themes resourcefolderIds(optional): Array of folder IDs to save the gamma inexportAs(optional):"pptx"or"pdf"to generate an export URL
Returns:
{
"success": true,
"generationId": "gen_abc123",
"gammaUrl": "https://gamma.app/docs/...",
"exportUrl": "https://gamma.app/export/...",
"credits": {
"deducted": 10,
"remaining": 90
}
}
Development
Project Structure
gamma-mcp-server/
├── src/
│ ├── index.ts # Entry point
│ ├── app.module.ts # NestJS app module
│ ├── gamma-api.service.ts # Gamma API client
│ ├── folders.resource.ts # Folders MCP resource
│ ├── themes.resource.ts # Themes MCP resource
│ └── generate.tool.ts # Generate MCP tool
├── dist/ # Compiled output
├── package.json
├── tsconfig.json
└── README.md
Scripts
yarn build- Compile TypeScript to JavaScriptyarn start- Run the compiled serveryarn dev- Run in development mode with ts-nodeyarn watch- Watch mode for TypeScript compilation
Troubleshooting
"Invalid API key" error
Make sure you've replaced the placeholder API key in src/gamma-api.service.ts with your actual Gamma API key.
Server won't start
- Make sure you've run
yarn installandyarn build - Check that port 3000 is not already in use
- Check the console for error messages
Claude Desktop can't connect
- Verify the absolute path in your Claude config is correct
- Make sure the server is built (
yarn build) - Restart Claude Desktop after editing the config
- Check Claude Desktop logs for connection errors
Learn More
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.