Skip to main content
Glama
gamma-mcp-server
by Arkava-AI

Gamma MCP Server

License: MIT Node.js Version TypeScript npm version npm downloads CI MCP SDK

A Model Context Protocol (MCP) server that integrates Gamma.app with AI assistants. Create presentations, documents, webpages, and social posts directly from your AI conversations.

Works with: Claude Code, Claude Desktop, OpenCode, GitHub Copilot CLI, Google Gemini CLI, and any other MCP-compatible AI assistant.

Features

  • Generate Content: Create professional presentations, documents, webpages, and social posts from text prompts

  • Theme Support: Browse and apply visual themes to your content

  • Folder Organization: Save generated content to specific folders

  • Template Remix: Create variations of existing Gamma templates

  • Email Sharing: Share generated content directly via email

Related MCP server: Gamma MCP Server

Quick Start

1. Clone and Install

git clone https://github.com/Arkava-AI/gamma-mcp-server.git
cd gamma-mcp-server
npm install
npm run build

2. Get Your Gamma API Key

  1. Log in to gamma.app

  2. Go to Settings > API (or Settings > Members > API tab)

  3. Click Create API key

  4. Copy the key (format: sk-gamma-xxxxxxxx)

Note: Requires Gamma Pro, Ultra, Team, or Business account.

3. Configure Your AI Assistant

Choose your AI assistant below for setup instructions.


Claude Desktop (macOS / Windows / Linux)

Config File

OS

Path

macOS

~/Library/Application Support/Claude/claude_desktop_config.json

Linux

~/.config/Claude/claude_desktop_config.json

Windows

%APPDATA%\Claude\claude_desktop_config.json

Add to the mcpServers object:

{
  "mcpServers": {
    "gamma": {
      "command": "node",
      "args": ["/absolute/path/to/gamma-mcp-server/dist/index.js"],
      "env": {
        "GAMMA_API_KEY": "sk-gamma-your-api-key-here"
      }
    }
  }
}

Restart Claude Desktop

Restart Claude Desktop to load the new MCP server. You should see "gamma" in your MCP servers list.


Claude Code

Claude Code uses the same MCP configuration as Claude Desktop. If you've already configured Claude Desktop, you're all set.

For project-level configuration, create a .claude/settings.json file in your project directory with the same mcpServers structure shown above. This allows different projects to use different MCP server configurations.


OpenCode

Config File

Scope

Path

Global (user)

~/.config/opencode/opencode.json

Project

./opencode.json (in your project root)

JSON Structure

{
  "mcp": {
    "gamma": {
      "type": "local",
      "command": ["node", "/absolute/path/to/gamma-mcp-server/dist/index.js"],
      "enabled": true,
      "environment": {
        "GAMMA_API_KEY": "sk-gamma-your-api-key-here"
      }
    }
  }
}

Note: OpenCode uses a different config format from Claude Desktop — mcp (not mcpServers), type field required ("local" or "remote"), command is an array, and env vars go under environment.

Restart OpenCode after editing the config to load the server.


GitHub Copilot CLI

Config File

  • ~/.copilot/mcp-config.json

JSON Structure

{
  "mcpServers": {
    "gamma": {
      "type": "local",
      "command": "node",
      "args": ["/absolute/path/to/gamma-mcp-server/dist/index.js"],
      "env": {
        "GAMMA_API_KEY": "sk-gamma-your-api-key-here"
      },
      "tools": ["*"]
    }
  }
}

Note: Requires the GitHub Copilot CLI (gh copilot) — not the same as OpenAI Codex.


OpenAI Codex

Config File

  • ~/.codex/config.toml (TOML format, not JSON)

TOML Structure

[mcp_servers.gamma]
command = "node"
args = ["/absolute/path/to/gamma-mcp-server/dist/index.js"]
enabled = true

[mcp_servers.gamma.env]
GAMMA_API_KEY = "sk-gamma-your-api-key-here"

Note: Codex uses TOML format, not JSON. The env section is a separate table under [mcp_servers.gamma.env].


Google Gemini CLI

Config File

Scope

Path

User

~/.gemini/settings.json

Project

.gemini/settings.json (in your project root)

JSON Structure

{
  "mcpServers": {
    "gamma": {
      "command": "node",
      "args": ["/absolute/path/to/gamma-mcp-server/dist/index.js"],
      "cwd": "/absolute/path/to/gamma-mcp-server",
      "env": {
        "GAMMA_API_KEY": "sk-gamma-your-api-key-here"
      },
      "timeout": 30000
    }
  }
}

Restart Gemini CLI after editing the config to load the server.


Available Tools

Tool

Description

gamma_generate

Create presentations, documents, webpages, or social posts

gamma_get_status

Check generation progress (with optional polling)

gamma_from_template

Remix existing Gamma templates

gamma_list_themes

Browse available visual themes

gamma_list_folders

List your Gamma folders

gamma_share_email

Share content via email

gamma_health

Verify server and API are reachable

gamma_archive

Archive a Gamma from your workspace

gamma_generate

Create new content using Gamma's AI.

Formats & Sizes:

  • presentation: fluid, 16x9, 4x3

  • document: fluid, pageless, letter, a4

  • social: 1x1, 4x5, 9x16

  • webpage: fluid

Example prompts in your AI assistant:

  • "Create a 5-slide presentation about sustainable energy"

  • "Generate a document explaining our Q1 results"

  • "Make a social media post announcing our new product"

gamma_get_status

Check if a generation has completed. Set waitForCompletion: true to automatically poll until done.

gamma_from_template

Remix an existing Gamma with new content or variable substitutions.

{
  "templateId": "gamma_xyz789",
  "prompt": "Update for Q1 2025",
  "variables": { "company_name": "Acme Corp" }
}

Multi-Machine Setup

This repository is designed for easy deployment across multiple machines:

# On each machine:
git clone https://github.com/Arkava-AI/gamma-mcp-server.git
cd gamma-mcp-server
npm install && npm run build

# Then configure your AI assistant with the local path

To update on any machine:

git pull
npm install
npm run build
# Restart your AI assistant

Environment Variables

Variable

Default

Description

GAMMA_API_KEY

(required)

Your Gamma API key (sk-gamma-...)

GAMMA_API_BASE_URL

https://public-api.gamma.app/v1.0

Override for self-hosted Gamma instances

GAMMA_POLL_INTERVAL_MS

2000

Milliseconds between status polls (default 2s)

GAMMA_MAX_POLL_ATTEMPTS

150

Max polling attempts before timeout (default 150 × 2s = 5 min)


Development

# Run in development mode with auto-reload
npm run dev

# Build for production
npm run build

# Run linting
npm run lint

# Format code
npm run format

# Type check
npm run typecheck

# Test with MCP Inspector
npm run inspect

Project Structure

gamma-mcp-server/
├── src/
│   ├── index.ts          # Main entry point
│   ├── constants.ts      # Configuration constants
│   ├── types.ts          # TypeScript interfaces
│   ├── schemas/          # Zod validation schemas
│   ├── services/         # API client and formatters
│   └── tools/            # MCP tool implementations
├── dist/                 # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
└── eslint.config.js

API Credits

Gamma uses a credit-based system for API usage. Credits are consumed per generation. Monitor your usage in the Gamma dashboard and enable auto-recharge if needed.


Troubleshooting

Error

Solution

"GAMMA_API_KEY environment variable is required"

Ensure env.GAMMA_API_KEY is set in your AI assistant's MCP config

"Invalid API key"

Keys should start with sk-gamma-. Verify the complete key.

"Rate limit exceeded"

Wait a few minutes. Contact Gamma support for higher limits.

"Insufficient credits"

Top up credits or enable auto-recharge in Gamma settings.


Requirements

  • Node.js 18+

  • Gamma Pro/Ultra/Team/Business account (for API access)

  • MCP-compatible AI assistant (Claude Code, Claude Desktop, OpenCode, GitHub Copilot CLI, Gemini CLI, etc.)


Maintainer

Arkava Ltd — engage@arkava.ai


License

MIT License - see LICENSE for details.


Available Tools

8 tools
gamma_archiveArchive GammaA
DestructiveIdempotent

Archive a Gamma (presentation, document, webpage, or social post) from your workspace.

Archived content is removed from your active workspace but retained for recovery. Use this to declutter your Gamma dashboard.

Inputs: gammaId (required), response_format.

gamma_from_templateCreate from TemplateA

Create new content by remixing an existing Gamma template.

This tool uses Gamma's Remix feature to create a new version of existing content with customizations. Useful for creating variations of proven templates.

PARAMETERS:

  • templateId (required): ID of the existing Gamma to use as template

  • prompt: Additional instructions for customization

  • variables: Key-value pairs for dynamic content substitution

  • folderId: Folder to save the result

  • waitForCompletion: If true, waits for completion

RETURNS: Same as gamma_generate

EXAMPLE: { templateId: "gamma_xyz789", prompt: "Update for Q1 2025 results", variables: { "company_name": "Acme Corp", "quarter": "Q1 2025" } }

Inputs: templateId (required), prompt, folderId, variables, +2 more.

gamma_generateGenerate Gamma ContentA

Create a new presentation, document, webpage, or social post using Gamma's AI.

This tool generates professional content from any text input - a one-line prompt, messy notes, or polished content. Gamma's AI will structure, design, and style your content automatically.

SUPPORTED FORMATS:

  • presentation: Slide decks (sizes: fluid, 16x9, 4x3)

  • document: Reports, articles, essays (sizes: fluid, pageless, letter, a4)

  • webpage: Websites with header/footer support (size: fluid)

  • social: Social media posts (sizes: 1x1, 4x5, 9x16)

PARAMETERS:

  • prompt (required): Your content or instructions. Can be brief ("Company overview presentation") or detailed with bullet points.

  • format (required): One of presentation, document, webpage, social

  • cards: Number of slides/sections (1-60, default: AI-determined)

  • size: Aspect ratio appropriate for the format

  • themeId: Visual theme ID (use gamma_list_themes to see options)

  • language: Target language code (en, es, fr, de, zh, ja, etc.)

  • imageStyle: auto, photographic, generated, clipart, none

  • cardDensity: auto, high, low

  • waitForCompletion: If true, waits up to 5 min for generation to complete

RETURNS:

  • generationId: ID for tracking/status checks

  • status: pending, completed, or failed

  • url: Link to view content (when completed)

  • title: Generated or custom title

EXAMPLES:

  1. Quick presentation: { prompt: "5 slide pitch deck for AI startup", format: "presentation" }

  2. Detailed document: { prompt: "Technical documentation for REST API...", format: "document", cards: 10 }

  3. Styled content: { prompt: "Company culture overview", format: "presentation", themeId: "theme_123", waitForCompletion: true }

CREDITS: Each generation consumes Gamma API credits based on complexity.

Inputs: no named parameters.

gamma_get_statusGet Generation StatusA
Read-onlyIdempotent

Check the status of a Gamma generation.

Use this tool to check if a previously started generation has completed. Generations typically take 30 seconds to 2 minutes depending on complexity.

PARAMETERS:

  • generationId (required): The ID returned from gamma_generate

  • waitForCompletion: If true, polls until complete (max 5 minutes)

RETURNS:

  • status: pending, completed, or failed

  • url: Link to view content (when completed)

  • title: Content title

  • creditsUsed: Credits consumed

EXAMPLE: { generationId: "gen_abc123", waitForCompletion: true }

Inputs: generationId (required), response_format, waitForCompletion.

gamma_healthHealth CheckA
Read-onlyIdempotent

Check if the Gamma MCP server and API are reachable and working.

Use this to verify your configuration is correct before running other tools. Returns whether the API key is valid, the API is reachable, and the account status.

Useful for:

  • Confirming the server is running after startup

  • Troubleshooting connection issues

  • Verifying your GAMMA_API_KEY is valid

Inputs: response_format.

gamma_list_foldersList Gamma FoldersA
Read-onlyIdempotent

List your Gamma folders for organizing content.

Folders help organize generated content. Use the returned folder IDs with gamma_generate's folderId parameter to save content to specific folders.

PARAMETERS:

  • limit: Max folders to return (1-100, default 20)

  • offset: Skip this many folders for pagination

RETURNS:

  • items: Array of folders with id, name, itemCount

  • total: Total number of folders

  • hasMore: Whether more folders are available

  • nextOffset: Offset for next page

EXAMPLE: { limit: 20, response_format: "json" }

Inputs: limit, offset, response_format.

gamma_list_themesList Gamma ThemesA
Read-onlyIdempotent

List available visual themes for Gamma content.

Themes control the visual styling of generated content including colors, fonts, and layouts. Use the returned theme IDs with gamma_generate's themeId parameter.

PARAMETERS:

  • limit: Max themes to return (1-100, default 20)

  • offset: Skip this many themes for pagination

RETURNS:

  • items: Array of themes with id, name, description

  • total: Total number of themes available

  • hasMore: Whether more themes are available

  • nextOffset: Offset for next page

EXAMPLE: { limit: 10, response_format: "markdown" }

Inputs: limit, offset, response_format.

gamma_share_emailShare Gamma via EmailA

Share a generated Gamma with recipients via email.

Send an email invitation to view your Gamma content. Recipients will receive a link to access the content.

PARAMETERS:

  • generationId (required): The ID of the Gamma to share

  • emails (required): Array of email addresses (max 10)

  • message: Optional personal message to include

RETURNS:

  • success: Whether the share was successful

  • emails: List of recipients

EXAMPLE: { generationId: "gen_abc123", emails: ["colleague@company.com", "client@example.com"], message: "Here's the presentation we discussed" }

NOTE: Ensure the generation is complete before sharing. Use waitForCompletion: true to automatically wait up to 5 minutes.

Inputs: emails (required), generationId (required), message, response_format, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool serves a distinct purpose: creating from prompt or template, checking status, listing themes/folders, sharing, health check, and archiving. No overlap detected.

    Naming Consistency5/5

    All tools follow the consistent pattern 'gamma_verb_noun' using snake_case, e.g., gamma_generate, gamma_list_themes, gamma_share_email.

    Tool Count5/5

    With 8 tools, the surface is well-scoped for a Gamma content generation server, covering creation, status, discovery, sharing, and archiving without bloat.

    Completeness4/5

    Core lifecycle is covered (create, check, archive, share), but missing a tool to list existing generations or browse created content, which is a minor gap.

    Related MCP Connectors

    Related MCP Servers