About Kagent Vision
Kagent Vision is an MCP server in the Files category: a KAgent Agent with Vision - Capture photos, transform them with Nano Banana, animate them with Veo3. Supports ASL.
Install
git clone https://github.com/automateyournetwork/kagent_visionThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (10)
asl_understandASL interpretation from frame sequence
Parameters not published.
banana_generateAI image generation/transformation (Gemini 3 Pro Image)
Parameters not published.
list_camerasProbe camera indexes, report which are available
Parameters not published.
list_imagesScan a directory for image files
Parameters not published.
veo_generate_videoAI video generation (Veo 3.1)
Parameters not published.
vision_burstCapture N frames at interval to `outputs/`
Parameters not published.
vision_captureCapture a single frame to `outputs/`
Parameters not published.
vision_startOpen a camera with configurable size/fps/backend
Parameters not published.
vision_statusCheck if camera is open, show properties
Parameters not published.
vision_stopRelease the camera
Parameters not published.
Ask AI
Ask AI about Kagent Vision
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.