Multimodal
Connects Claude to OpenAI, xAI, Gemini, ElevenLabs, and BFL APIs for generating and editing images, videos, audio, and transcriptions through a single interface. Exposes tools like generate_image, generate_video, generate_audio, and transcribe_audio with automatic provider selection based on which API keys you've configured. You can explicitly choose a provider per request or let it auto-select from what's available. All generated media saves to disk with descriptive filenames. Reach for this when you want Claude to generate visual or audio content without writing provider-specific code for each API, or when you're working across multiple media generation services and want consistent tool parameters.
- GitHub stars
- 1
- tools
- 5
- auth
- Secret needed
- transport
- STDIO
- env vars
- 6
- last updated
- Mar 3, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
generate_imageGenerate an image from a text prompt.
Generate an image from a text prompt.
No parameter schema in public metadata yet.
generate_videoGenerate a video from a text prompt. Video generation is asynchronous and may take several minutes.
Generate a video from a text prompt. Video generation is asynchronous and may take several minutes.
No parameter schema in public metadata yet.
generate_audioGenerate audio from text. Supports text-to-speech and sound effects. Audio generation is synchronous.
Generate audio from text. Supports text-to-speech and sound effects. Audio generation is synchronous.
No parameter schema in public metadata yet.
transcribe_audioTranscribe audio to text (speech-to-text).
Transcribe audio to text (speech-to-text).
No parameter schema in public metadata yet.
list_providersList all configured media generation providers and their capabilities. Takes no parameters.
List all configured media generation providers and their capabilities. Takes no parameters.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
OPENAI_API_KEYsecretOpenAI API key for image, video, audio generation and transcription
XAI_API_KEYsecretxAI API key for image and video generation
GEMINI_API_KEYsecretGoogle Gemini API key for image, video, and audio generation
ELEVENLABS_API_KEYsecretElevenLabs API key for audio generation and transcription
BFL_API_KEYsecretBFL API key for FLUX image generation and editing
MEDIA_OUTPUT_DIRDirectory for saved media files (defaults to cwd)
Readme
multimodal-mcp
Multi-provider media generation MCP server. Generate images, videos, audio, and transcriptions from text prompts using OpenAI, xAI, Gemini, ElevenLabs, and BFL (FLUX) through a single unified interface.
Features
- 🎨 Image Generation — Generate images via OpenAI (gpt-image-1), xAI (grok-imagine-image), Gemini (imagen-4), or BFL (FLUX Pro 1.1)
- ✏️ Image Editing — Edit images via OpenAI, xAI, Gemini, or BFL (FLUX Kontext)
- 🎬 Video Generation — Generate videos via OpenAI (sora-2), xAI (grok-imagine-video), or Gemini (veo-3.1)
- 🔊 Audio Generation — Text-to-speech via OpenAI (tts-1), Gemini, or ElevenLabs (Flash v2.5). Sound effects via ElevenLabs
- 🎙️ Audio Transcription — Speech-to-text via OpenAI (Whisper) or ElevenLabs (Scribe)
- 🔄 Auto-Discovery — Automatically detects configured providers from environment variables
- 🎯 Provider Selection — Auto-selects or explicitly choose a provider per request
- 📁 File Output — Saves all generated media to disk with descriptive filenames
Quick Start
Set the API key for at least one provider. Most users only need one — add more to access additional providers.
Details
- Repository
- github.com/rsmdt/multimodal-mcp
- Category
- Media & Entertainment
- Package
@r16t/multimodal-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related Media & Entertainment MCP servers
View all
mediasensejoaoestella/mediasenseLet Claude listen to audio and watch video: transcribe, summarize and edit recordings and links.1stars
Rendobarrendobar/mcpTransform video, audio and images, and generate media from prompts. FFmpeg, captions, models.0stars
Mcp Serversocialneuron/mcp-server52 MCP tools for AI social media: create, distribute, analyze, and optimize content.0stars
Contendeo0xkaroshi/contendeo-mcpMultimodal video analysis MCP — transcription, vision, and OCR for any video URL.0stars
avotsavotsai/avots-mcpImage, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance.0stars