"Sage" matching MCP servers:

Reads website pages and generates one cohesive image per page, with no text and no recognizable human faces.

Orchestrates 3D scene creation, camera paths, and physics-driven animations, bridging physics simulations with video rendering by defining scene graphs, binding objects to physics bodies, and exporting to React Three Fiber or Remotion.

A privacy-conscious MCP server that enables image analysis via Google Gemini with safety features like two-step confirmation and SSRF defenses.

A local MCP server for the Windows version of Sky: Children of the Light that enables AI clients to read validated game windows, perform local OCR, and send limited game keystrokes or chat text when explicitly permitted.

Enables AI video and image generation in MCP clients like ChatGPT, Claude, Cursor, and Antigravity through one OAuth endpoint, offering 16 models with upfront cost details.

Runs a local MCP service for video understanding, letting agents queue video analysis tasks, watch local videos, and retrieve cursor-based event results without uploading footage to the cloud.

Enables AI assistants to perform local computer-vision-based image recognition and editing, including cropping, resizing, rotating, background removal, drawing text and shapes, object detection, OCR, overlays, and metadata inspection without sending images to external servers.

Safe Vision MCP enables safe and efficient local image inspection by generating thumbnails, contact sheets, and statistics, avoiding large images in LLM context.

Provides structured visual analysis tools for coding agents, enabling UI analysis, screenshot comparison, OCR, and crop-based refinement through VLM.