Enables AI assistants to inspect, convert, resize, crop, merge, extract and OCR local images, PDFs, audio and video entirely on the user's machine. Modules can be toggled individually, and all operations stay within a sandboxed working folder with atomic writes and no data sent anywhere.
MCP server exposing headless ffmpeg operations for video, audio, and image processing via auto-generated typed tools, enabling agentic media file manipulation.
Deterministic Model Context Protocol (MCP) server for FFmpeg. Gives AI agents 17 structured tools with hardware acceleration for video conversion, compression, waveforms, subtitles, and inspection.
Enables AI agents to create isolated Docker runtimes, execute commands, manage workspace files, drive a headed browser, and retrieve artifacts through eight semantic MCP tools, with progressive capability discovery and explicit sandbox lifecycle.
Runs entirely local media tooling as an MCP plugin: it edits and inspects video, denoises/transcribes/normalizes audio, generates images, performs OCR, does offline text-to-speech, drives the user's logged-in Chrome via CDP, and reads or creates Office and PDF documents. Everything executes on the machine through ffmpeg, faster-whisper, MossFormer2, ComfyUI/FLUX, Tesseract, SAPI and Playwright, with no API costs or file uploads.