"author:0rkz/byte-mcp-server" matching MCP servers:

Author, validate, preview, and render motion-graphics videos from a single JSON document (Clipkit Protocol). 16 tools with in-chat PNG previews, captions, templated promos, and hand-off to a free browser editor by link.

Enables AI agents to author node-graph-based procedural graphics as data and render them deterministically via a pinned headless engine, returning validated, hashed image artifacts with full provenance.

Provides an MCP server for local low-power screen vision, enabling AI agents to perform OCR and UI detection on inaccessible screens (games, remote desktops) using NPU acceleration and system OCR.

Enables agents to author, validate, inspect, patch, and render editable JSON pixel-art and animation recipes through local tools, producing PNG contact sheets, APNGs, sprite atlases, and related export bundles.

Enables local magic-byte file identification, Office document metadata and provenance inspection, and lossless removal of identifying image metadata. It performs bounded, local-only inspection without external dependencies.

Enables agents to compress JPEG, PNG, and WebP images to a target byte size, split PDFs by page or ranges, and remove image metadata while processing local files without sending file bytes over the network.

This MCP server lets an agent validate a local image's format, byte size, and pixel dimensions against published upload limits, and draft a cautious Basic or Pro enhancement plan from a blur description. It also surfaces the official site, pricing, and contact links, all without uploading or processing any image pixels.

Enables MCP clients to open, read, edit, verify, and save Aegisub/ASS subtitle documents, covering event lines, styles, timing and QC, karaoke, override tags, vector drawings, clipping, and font metrics. Includes a libass-backed verification layer and byte-faithful round-trips, served over stdio or streamable HTTP.

Exposes a shared video-editing timeline as MCP tools, letting Claude Code, Codex or any MCP client cut, trim, layer, caption, mix and generate motion graphics on the same versioned project the browser editor has open. Every edit an agent makes shows up live, is labelled with its author, and can be undone.

Enables an agent to author, render, and visually verify Manim animations from a described concept, returning evidence and structured verdicts so incorrect renders can be fixed before export.

Converts video and image files through the grey telecinema presets (NTSC-J seated black, 8-bit grey, 1-bit overcalc, and a 4x4 collage), producing silent, dither-free output suitable for AI models to ingest. Every conversion is logged with its full command line to an always-visible SQLite index, so byte and dimension changes between files can be audited at any time.

Enables AI assistants to control Adobe After Effects through MCP, including creating and modifying compositions, layers, masks, cameras, and animations, plus an English-to-Vietnamese text layer localization toolset.

Enables AI agents to author, validate, render, measure, and fix 2D rigs and animations through 16 tools, returning results as images and providing a live editor bridge.

Enables AI agents to author and refine JSON-based motion-graphics compositions by editing layers, keyframes, easing curves, text animators, masks, effects, and other animation properties, then previewing rendered frames or video output.

Enables Claude to inspect and build compositions in an open Adobe After Effects project, animate layers and effects, preview real frames, compare against reference video side by side, measure and recreate camera moves, detect cuts and beats, and render MP4s.

Enables Windows MCP clients to author MikuMikuDance scenes by controlling characters, cameras, lighting, physics, timeline editing, MME effect assignments, and AVI video output through natural language or scripted tool calls.

Enables agents to create, inspect and edit Kdenlive project files, import and relink media, query installed MLT effects/transitions, author subtitles, and run asynchronous MLT renders, plus drive the live Kdenlive editor UI. Edits always write new files, and rendering is job-based with verification of the output.

Enables MCP clients and AI agents to author, inspect, validate, and render PromoShot .promo projects over stdio, delegating rendering to the promo CLI.

An MCP server for creative generation and video production, letting AI agents author declarative animations, render deterministic frames, and measure output quality with perception instruments for brand and accessibility conformance.

Enables AI assistants to read, audit, and byte-faithfully edit Warcraft III .w3x and .w3m maps while preserving untouched file bytes, with tools for metadata, objects, terrain, sounds, cameras, triggers, and more.

Enables AI agents to author designs as structured JSON scenes and render them to PNG, JPEG, WebP, vector PDF, animated PNG, GIF, MP4 or WebM at every target size, using one native binary with no browser or headless Chrome.

Enables Claude to create, edit, validate, and animate video projects through structured project files, including rendering frames or exports, inspecting previews, and applying themes, templates, effects, and subtitles.

Connects MCP clients to an interior design studio so users can upload room, home, or yard photos and generate photorealistic redesigns, paint and flooring previews, decluttering, virtual staging, and furniture shopping.

Enables users to author buildable QuadSpinner Gaea 2 .terrain projects, turn real DEM or synthetic elevation into Gaea-ready heightmaps and 16-bit erosion masks, have Gaea itself validate and build the project, and read back the exported heightmap and colour-map outputs. It bakes in the file-format, licence, schema-version and mask-bit-depth constraints that otherwise make Gaea-produced projects fail to open, build, or apply correctly.

Connects an AI client to a locally running Blender instance via a local MCP server plus addon, exposing scene queries, viewport previews and renders, file import/export, and script execution so the model can author its own modeling and material scripts. Defaults to a compact 12-tool script-oriented profile, with an optional compatibility mode exposing the full tool set.

Enables generating images, animations, PDFs, charts, and code-highlight SVGs from HTML/JSX templates and code, writing files atomically and returning paths, MIME types, and byte counts without embedding binary media in the agent context.

Enables read-only inspection of Xiaohongshu posts via MCP, retrieving titles, content, author, engagement data, comments, images, and video frames from share links or xsec_token URLs.