Skip to content
mcp/skillhub

Multimodal MCP Server

by rsmdtio.github.rsmdt/multimodalv1.3.1

Multi-provider media generation — images, video, audio, and transcription via a unified interface

2Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Stale7mo ago

Install Multimodal MCP server

Install in Claude Code

claude mcp add multimodal -e OPENAI_API_KEY='<openai-api-key>' -e XAI_API_KEY='<xai-api-key>' -e GEMINI_API_KEY='<gemini-api-key>' -e ELEVENLABS_API_KEY='<elevenlabs-api-key>' -e BFL_API_KEY='<bfl-api-key>' -- npx -y @r16t/multimodal-mcp

Configuration

VariableRequiredSecretDescription
OPENAI_API_KEY—yesOpenAI API key for image, video, audio generation and transcription
XAI_API_KEY—yesxAI API key for image and video generation
GEMINI_API_KEY—yesGoogle Gemini API key for image, video, and audio generation
ELEVENLABS_API_KEY—yesElevenLabs API key for audio generation and transcription
BFL_API_KEY—yesBFL API key for FLUX image generation and editing
MEDIA_OUTPUT_DIR——Directory for saved media files (defaults to cwd)

Freshness

Stale — last maintenance signal 7mo ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-03-05 · 7mo ago · GitHub

  2. Latest release

    2026-03-05 · 7mo ago · GitHub · v1.4.0

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-03-03 · 7mo ago · official registry · v1.3.1

FAQ

›How do I install the Multimodal MCP server in Claude Code?

Run: claude mcp add multimodal -e OPENAI_API_KEY='<openai-api-key>' -e XAI_API_KEY='<xai-api-key>' -e GEMINI_API_KEY='<gemini-api-key>' -e ELEVENLABS_API_KEY='<elevenlabs-api-key>' -e BFL_API_KEY='<bfl-api-key>' -- npx -y @r16t/multimodal-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does Multimodal require an API key?

Yes. It expects OPENAI_API_KEY, XAI_API_KEY, GEMINI_API_KEY, ELEVENLABS_API_KEY, BFL_API_KEY, of which 5 are secrets.

›Can I use Multimodal as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Multimodal in the official MCP registry?

Yes, as io.github.rsmdt/multimodal.

Alternatives to Multimodal

Other images, video & audio MCP servers.

View all