MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for Keyframe.it — let Claude (or any MCP client) rig, animate and export 2D skeletal animations in the free Keyframe.it editor, rig, animate, play-test and export pixel-art sprites in Sprite Puppeteer, and rig and animate 3D models in MeshForge
npm MIT -
Local-first MCP server for video: download any video from almost any URL, or turn it into a transcript and the handful of keyframes that matter. YouTube, TikTok, Instagram, X, Facebook, WeChat Channels, direct MP4/HLS. No cloud, no API keys.
npm MIT -
Turn a screen recording into annotated keyframes a coding agent can read. MCP server + CLI.
npm MIT -
Open-source 2D animation editor. Create with Claude Code or Codex via MCP, then refine layers and keyframes visually.
MIT ★ 8 -
Local-first MCP server that turns video into queryable context with transcripts, keyframes, OCR, and semantic search.
MIT ★ 3 -
Turn any video into timestamped transcripts and keyframe contact sheets for AI agents—offline, local-first, no API key required.
MIT -
anni.run – CSS animation editor for coding agents: tune keyframes on a timeline over your real page, your agent writes them back.
npm ★ 1 -
Let Claude watch videos: timestamped transcript, scene-selected keyframes, exact frames and OCR. Local, no API keys. MCP server + skill + Claude Code plugin.
MIT ★ 3 -
mcp-videogithub.com/ipythonist/mcp-videoupdated this year
MCP server for video intelligence — analyze any video with AI vision. Extract keyframes, transcripts, and trading strategies from YouTube, Instagram & 1000+ sites.
MIT ★ 4 -
Let AI watch videos: local files or YouTube/Bilibili URLs -> timestamped transcript + keyframes + contact sheets. Offline, no API key. MCP server + CLI + agent skill.
MIT ★ 12 -
An MCP server that gives AI agents local video tools: metadata, shot detection, frame extraction, and keyframe checks. Runs FFmpeg on your machine. No API key.
MIT ★ 1 -
MCP server that lets AI assistants animate in OpenToonz: editable vector levels, xsheet timing, real keyframes, anatomy-accurate character rigs with walk and run cycles, physics, and studio looks built from OpenToonz fx.
pypi MIT ★ 4 -
Create keyframe animations from hand-drawn Excalidraw diagrams — timeline editor, camera animation, sequence reveals, and an MCP server for AI-driven creation with real-time live preview Export as MP4, WebM, GIF, or animated SVG.
npm MIT ★ 103 -
Local-first MCP server for video: download any video from almost any URL, or get a transcript plus scene-aware deduplicated keyframes. YouTube, TikTok, Instagram, X, WeChat Channels, MP4/HLS. No cloud, no API keys.
npm MIT ★ 11 -
anni.run – a CSS animation editor for coding agents (Claude Code, Codex, Cursor): your agent opens the animations from your project, you tune keyframes, timing and easing on a timeline over your real page, the agent writes them back. This package is the M
npm MIT -
Turn a screen recording into annotated keyframes a coding agent can read. MCP server + CLI.
MIT ★ 4 -
Let any LLM watch a video: scene-aware keyframes, storyboards, and timestamped transcripts, via MCP or any provider's API.
MIT -
Recordings in. Agent-ready evidence out. Local-first MCP for transcripts, keyframes, OCR, speakers, and wall-clock evidence.
MIT ★ 34 -
weixin-articles-mcpgithub.com/jj-cheng25/weixin-articles-mcpupdated this year
MCP server for reading WeChat (微信) Official Account articles with native multimodal output - images and video keyframes as content blocks, not URLs.
MIT ★ 13 -
Turn any video URL into an AI-ready transcript and keyframe images via a local MCP server, no cloud or API keys.
MIT -
Bring AI to your Minecraft cinematics: a local MCP server for Flashback replay editing, camera paths, keyframes and video exports. 22 tools, no npm dependencies, English and Italian setup guides.
NOASSERTION ★ 2 -
claude-real-videono update data
Let any LLM agent actually watch videos. The watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally (ffmpeg + Whisper), cached per source. Requires Python 3.10+ and ffmpeg; runs via uvx from PyPI (claude-real-video).
smithery -
Local AI Worker & MCP Server for Adobe After Effects. Transform natural language prompts into automated 2D character rigging, audio lip-sync, and live keyframes using Ollama (Qwen) & Windows COM.
-
A Model Context Protocol (MCP) server & bridge connecting AI assistants (Claude, Antigravity, Cursor) directly to Cavalry 2D. Programmatically generate procedural motion graphics, kinetic typography, node connections, keyframes, and batch renders via natural language.
★ 2 -
An MCP server that lets AI read, view and edit a live Adobe After Effects project — inspect comps, render frames, write keyframes and expressions, and build projects end to end. Works with Claude Code or any MCP client.
MIT ★ 89 -
MCP server for Google Flow (Veo 3 / Omni 1.1): batch video generation from Claude Code and Claude Desktop through the OmniFlow Chrome extension. The missing Google Flow API — prompts, queue, keyframes, auto-download on your own Google AI plan.
npm MIT -
Gemini Omni 1.1 Flash API Python SDK and MCP server for Google's newly announced update: scene extension, keyframe control, 360p draft mode, 4K upscaling, and video reference input via MuAPI.
MIT ★ 4 -
MCP server that lets Claude and other AI assistants build, animate, preview and render motion graphics in a live Adobe After Effects project: 79 tools for comps, layers, keyframes, springs, text reveals, transitions, masks, effects, layout, 3D cameras, beat-synced audio and checked aerender renders.
MIT ★ 14 -
Premiere-MCP-IMT + SKILLS — Premiere Pro for AI agents. Every Adobe UI language; vision: draws Object Masks on what it sees, places speed keyframes on the timeline by sight. A large skills library, built for Adobe's generative features (Generative Extend, Generative Media, Object Mask, Enhance Speech). ~440 verified operations. macOS + Windows.
Apache-2.0 -
Kling API examples by useapi.net: Kling 4.0, 3.0 and Omni video (text-to-video, image-to-video with keyframes, multi-shot, motion control, native sound), lip-sync avatars, KOLORS images and a hosted MCP server (45 tools), on your Kling AI subscription, with no Kling developer account.
MIT ★ 1 -
Non-linear video editor an AI agent can actually drive (MCP), with a web UI. Timeline -> ffmpeg.
pypi MIT -
svgshotgithub.com/BusyBee3333/svgshotupdated this year
SVGShot — Animated SVG creator & screenshot tool with CSS animation-aware capture. Render, filmstrip, and diff animated SVGs the way users actually see them.
Apache-2.0 ★ 1