"Sky" matching MCP servers:

本地MCP工具，通过截图、OCR、键盘和聊天输入与PC游戏《光遇》交互，支持AI客户端陪聊和实验。

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.

Local-first MCP server that turns raw drone footage into a polished marketing cut through conversational interaction with Claude.

Official MCP server for the Pedra API, enabling AI real-estate photo editing (virtual staging, renovation, room emptying, enhancement, sky replacement, object removal/blur, and property videos) directly from Claude, ChatGPT, Cursor, and other MCP clients.

Enables AI agents to drive Adobe Photoshop on macOS through natural language, covering autonomous Adobe Firefly generative fill and object removal, Sensei AI sky and subject selection, non-destructive layer, adjustment, and text tooling, plus photographic workflows like sky harmonization and distraction removal. It also supports full document management, Camera Raw adjustments, and raw ExtendScript execution for custom operations.

Gives MCP clients a suite of AI photo-editing and design tools — background removal, upscaling, object/watermark erasing, sky and background replacement, retouching, generative fill — along with multi-layer design composition and rendering to PNG, JPEG or PDF. Every call is proxied with an API key to the snapnedit API, so no models run locally.

Enables AI agents to drive Adobe Lightroom Classic directly — searching and organizing catalogs, reading and writing the full set of develop parameters, building geometric and AI-generated masks (sky, subject, mountains, water, people), applying presets, and rendering previews, histograms, and exports. All capabilities are exposed as 167 MCP tools over a Lua plugin bridge, with write-confirmation sentinels so silently dropped edits surface as explicit errors.

Production-grade MCP server wrapping SkyFi's satellite imagery platform API. Enables AI agents to conversationally search, price, order, and monitor satellite imagery through the Model Context Protocol.

Lets AI assistants render HTML animations to MP4 or GIF in 16:9, 9:16 and 1:1, preview single frames to check their own work, and finish videos with royalty-free music, AI voiceover, burned-in captions, titles and logos. It renders code frame by frame in a real browser rather than generating video from a text prompt.

Local GGUF vision-language models behind one MCP server: captioning, visual question answering, object detection/pointing, gaze estimation and video classification, all on-device with no cloud API. Bundles a 403 MB SmolVLM so it works with nothing mounted.

Enables AI agents to perceive and quantitatively verify physical hardware through USB webcams and RTSP/HTTP network streams, returning inline image content plus numerical metrics such as brightness, contrast, edge density, motion, SSIM baseline comparisons, and OCR text. Agents can watch feeds for visual conditions, correlate buffered frames with serial/log/MQTT events, and apply privacy masks and access controls.