openrouter-mcp-multimodal
stabgan/openrouter-mcp-multimodal
Multimodal access to OpenRouter models: text chat, image, audio and video analysis, and image, audio and video generation (Veo, Sora, Seedance, Wan).
- Cloud integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 99
- Language
- TypeScript
- License
- Apache-2.0
- Forks
- 29
- Latest release
- v5.1.011d ago
- Activity
- updated 1d ago
- Platforms listed
- macOS, Windows, Linux
- claude
- llm
- mcp
- mcp-server
- model-context-protocol
- multimodal
- openrouter
- typescript
First MCP server?Start with the basics
Turn long videos into vertical shorts: moment detection, face-tracked 9:16 reframing, captions, dubbing and publishing to TikTok, Instagram and YouTube.
Omnimodal AIGC framework that turns ComfyUI workflows into MCP tools without code, for text, image, sound and video generation, with a Chainlit web interface.
Browser video editor driven through a JSON timeline: clips, keyframes, transitions, text animations, filters, reference-video analysis and ffmpeg export.
Computer vision-based image recognition and editing tools.
Drive Google Flow with your Google account: Veo text-to-video, image-to-video and clip extension, Imagen text-to-image, reusable characters and scenes.
Self-hosted AI studio exposing local image, video and music-video generation, upscaling, RAG and code intelligence, with renders queued on your own GPU.
Drive the WeftCut desktop video editor: trim and split clips, keyframes, effects, captions, audio mixing, markers and export, with live edits and dry runs.
Local-first AI media workbench with a canvas, short-form timeline editor and shared assets, controllable by agents.