MCP Server

Connect your AI tools to varg.ai for image, video, speech, and music generation — no code required. The varg MCP server gives any MCP-compatible client access to 19 tools with inline media previews.

Connect

Connect via Custom Connectors on claude.ai.

Open connectors

Go to Settings → Connectors in Claude.

Add custom connector

Click + → Add custom connector, then paste:

https://mcp.varg.ai/mcp

Authorize

Click Add. A browser window opens — log in to your varg.ai account and click Approve. You’re connected.

Available on Free, Pro, Max, Team, and Enterprise plans. Free users are limited to one custom connector.

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "varg": {
      "url": "https://mcp.varg.ai/mcp"
    }
  }
}

Restart Claude Desktop. A browser window opens — log in and click Approve.

On macOS, the config file is at ~/Library/Application Support/Claude/claude_desktop_config.json.

Connect via Custom Connectors on chatgpt.com.

Open connectors

Go to Settings → Connectors in ChatGPT.

Add custom connector

Click Add custom connector, then enter the server URL:

https://mcp.varg.ai/mcp

For Registration method, select DCR (Dynamic Client Registration). Leave Client ID and Client Secret blank.

Authorize

Click Add. A browser window opens — log in to your varg.ai account and click Approve. You’re connected.

Available on Free, Plus, Pro, and Team plans. You can also use varg via the OpenAI Responses API by passing server_url directly.

Add the remote MCP server to your project’s .mcp.json:

{
  "mcpServers": {
    "varg": {
      "url": "https://mcp.varg.ai/mcp"
    }
  }
}

Or add via the CLI:

claude mcp add varg --url https://mcp.varg.ai/mcp

Claude Code will prompt you to authorize on first use.

For local mode without OAuth, use npx @vargai/mcp with stdio transport instead. See the Claude Code setup guide for the full skill installation.

Add to .vscode/mcp.json in your project:

{
  "servers": {
    "varg": {
      "url": "https://mcp.varg.ai/mcp"
    }
  }
}

Or add globally via command line:

code --add-mcp '{"name":"varg","url":"https://mcp.varg.ai/mcp"}'

VS Code will prompt you to authorize on first use.

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "varg": {
      "url": "https://mcp.varg.ai/mcp"
    }
  }
}

Cursor will prompt you to authorize on first use.

Run the MCP server locally via stdio — no remote connection needed:

npx @vargai/mcp

Uses your API key from ~/.varg/credentials or VARG_API_KEY env var.Log in first if you haven’t:

bunx vargai login

Available tools

The MCP server exposes 23 tools:

Tool	Description
`generate_image`	Generate images with FLUX, Recraft, Seedream, Nano Banana, and more
`generate_video`	Generate videos with Kling v3, Minimax, Seedance, Sora, and more
`generate_speech`	Text-to-speech with ElevenLabs (50+ voices)
`generate_music`	Generate background music with MiniMax Music
`probe_media`	Inspect a video/audio file — duration, dimensions, codec, fps, bitrate
`trim_video`	Cut a segment from a video by start/end time or start/duration
`resize_video`	Scale a video to new dimensions (contain, cover, or stretch)
`slice_video`	Split a video into segments with first-frame thumbnails
`run_ffmpeg`	Run any FFmpeg command in the cloud (arbitrary filters, concat, extract audio, etc.)
`list_models`	List all available AI models with pricing
`check_balance`	Check your credit balance
`list_templates`	Browse video templates
`get_template`	Get template details and variables
`render_template`	Render a video from a template
`get_job`	Check generation job status
`list_voices`	List available TTS voices

Plus tools for lipsync, upscaling, transcription, and file uploads.

How it works

Your AI tool (Claude, ChatGPT, VS Code, Cursor)
    │
    │  OAuth 2.1 (automatic)
    ▼
mcp.varg.ai (MCP server)
    │
    │  API key (managed for you)
    ▼
api.varg.ai (varg API, /v2)
    │
    ▼
AI providers (fal, ElevenLabs, Higgsfield, HeyGen, PiAPI, etc.)

When you connect for the first time, the MCP server walks you through an OAuth flow:

You log in to your varg.ai account (or create one)
You approve the connection
An API key is created automatically and stored securely on the server
All subsequent requests use this key — no manual key management needed

Inline media previews

Tools that generate media return inline previews directly in your chat:

Images — displayed inline with click-to-open fullscreen
Videos — embedded player with play/pause controls
Audio — compact player with progress bar and seek

These work in Claude Desktop, claude.ai, and VS Code (via MCP Apps).

Pricing

varg uses a credit system. 1 credit = $0.01 USD.

Generation	Credits	Cost
Image (Flux Schnell)	5	$0.05
Image (Flux Pro)	10	$0.10
Image (Nano Banana Pro)	5	$0.05
Image (Recraft v3)	10	$0.10
Image (Recraft v4 Pro)	30	$0.30
Image (Grok Imagine)	3	$0.03
Video (Kling v3, 5s)	150	$1.50
Video (Kling v3 Standard, 5s)	100	$1.00
Video (Wan 2.5, 5s)	80	$0.80
Video (Minimax, 5s)	80	$0.80
Video (Seedance 2, 5s)	250	$2.50
Video (LTX-2, 5s)	50	$0.50
Speech (ElevenLabs v3)	25	$0.25
Speech (ElevenLabs Turbo)	20	$0.20
Music	30	$0.30
Lipsync (Sync v2 Pro)	80	$0.80
Lipsync (OmniHuman)	100	$1.00
Transcription (Whisper)	10	$0.10
Transcription (Groq Whisper Turbo)	3	$0.03
FFmpeg Trim	5	$0.05
FFmpeg Resize	5	$0.05
FFmpeg Slice	5	$0.05
FFmpeg (custom command)	5	$0.05
Probe Media	5	$0.05

Cached results are free. Use check_balance to see your remaining credits.

Get API Key

AI Models

Browse all available models with pricing

Templates

Pre-built video templates

API Reference

Full REST API documentation

Get Started

Models

SDK

Templates

MCP

AI Agents

Comparisons

Connect

Available tools

How it works

Inline media previews

Pricing

Get API Key

AI Models

Templates

API Reference

​Connect

​Available tools

​How it works

​Inline media previews

​Pricing

Get API Key

AI Models

Templates

API Reference

Connect

Available tools

How it works

Inline media previews

Pricing