Frame Check MCP server: deterministic structural framing analysis for AI-generated documents, with default-on frame-divergence block per FRAME_DIVERGENCE_CONTRACT_v1 c1.0. MCP surface delegates V4.2 judgment to the caller's agent model; zero Frame Check LLM cost per query.

MCP server that lets image-only models look at video: frames with timecodes, plus measurable video properties.

Structural framing analysis as an MCP server with deterministic detection. The caller's agent runs the judge, so Frame Check bears zero LLM cost per query.

⚡ 让你的视频秒变 60/120 帧丝滑高刷！免费开源的本地视频 AI 极速补帧神器，一键拯救 24/30fps 动漫与电影，支持 NVIDIA 显卡硬件加速与 HDR 画质，绿色免安装、开箱即用、自带桌面端与 MCP 接口！

MCP server for the Frame security scanner: scan, verify, fix, exploit, framework packs and the separation logic solver, from any MCP client.

Turn your Figma components into a design kit your AI coding agent follows.

AI-native MCP server for creative workstation telemetry—let Claude/Hermes monitor CPU/thermal, throttle background apps, alert Discord/Telegram. Python + Streamlit.

Video frame extraction & composition service for AI vision pipelines, extracts frames via FFmpeg and composes them into 1×1/2×2/4×4 grid sheets for multimodal LLMs. REST API, Web UI, and MCP server over one core engine.

Video inspection MCP server for AI agents. Search available captions, retrieve timestamped frames, and verify visual evidence locally.

Extract video frames and compose AI-readable grid sheets for multimodal LLM pipelines, self-hosted via REST, Web UI, or MCP.

Lightweight Android profiler and Layout Inspector in your browser, with MCP tools and an agent skill for AI agents: CPU, memory, frames, stalls, layouts, network and logcat over adb

MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.

CLI and MCP server that render store-ready App Store and Google Play screenshots from one config: device frames, benefit-driven headlines, exact store dimensions, incremental builds.

MCP server for Bezelbub: frame screenshots and screen recordings in Apple device bezels (iPhone, iPad, Mac, iMac, Apple TV device mockups), including transparent HEVC-alpha video export. macOS only.

Figma MCP: list frames in a file and fetch one frame's JSON and image safely. 2 tools.

Figma MCP server: list frames in a file and fetch one frame's JSON and image safely. Runs in production at Scalably.

See and check native iOS and Android UI from a coding agent, frame by frame. CLI and MCP server for Debug builds (Device DevTools Protocol).

Video link to answers over MCP: downloads with audio merged, transcribes, embeds frames and transcript with jina-embeddings-v4, and returns typed, timestamped evidence with the frames. 19 typed tools, resources and prompts.

PaKi Curator: MCP and A2A curator agent for César Yagüe's catalogue of contemplative moving-image works. Her curatorial voice draws from three layers: the catalogue, the curatorial capsules, and the measurements taken frame by frame from each master.

AfterEffects-MCP-IMT + SKILLS — After Effects for AI agents. Every Adobe UI language; vision: draws Object Matte on what it sees, syncs AI-generated layers with the plate frame by frame. A large skills library, built for Adobe's AI and generative features (Roto Brush, Object Matte, Content-Aware Fill). ~270 undo-safe operations. macOS + Windows.

Street Fighter 6 frame data API for GPT Actions / MCP integrations

Self-hosted YouTube research MCP with 17 tools for discovery, transcripts, frames, comments, and local semantic corpora.

Turn HTML prototypes into frame-perfect social videos, from a Studio app or any MCP client.

MCP server that turns any video (local file or URL) into frames + transcript for Claude.

Inspect Adobe Animate documents and edit frame scripts, timelines, tweens, and library items.

Structured thinking grids for AI agents - standalone MCP server, zero dependencies, deterministic v2 frames

MCP server that lets AI assistants watch YouTube videos (frames + audio) through Google Gemini.

Let Claude and other AI apps watch and listen to videos: transcripts, scene frames and sounds on one timeline.

News bias & framing diff across 50+ outlets per event

Local MCP server: turn screen recordings into transcript, exact frames, OCR and wall-clock evidence for coding agents.

Native Qt serial, network and SSH workbench with C-style frame scripts and shared AI/MCP access

HTTP security headers scanner API + MCP server: HSTS, CSP, framing, COOP/CORP and cookies, with a score and fix snippets.

Three.js MCP server — inspect scenes, live-preview tweaks and turn them into code. Website audits, video frame capture, Playwright helpers.

Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis

Let AI agents record the Windows screen, watch it as frames, and edit it with ffmpeg

MCP server that turns any video (file, URL, or Jira attachment) into frames + transcript for Claude Code

Local video review player that turns frame comments into a fix queue for coding agents (MCP server + Claude Code plugin).

Let AI agents read videos over MCP: transcripts, frames and sound from YouTube, web pages and local files.

Local-first YouTube research MCP server: search, metadata, transcripts with FTS search, media, frames and batch jobs via yt-dlp. No API key.

Give your model eyes for video: scene-change frames + tiled contact sheets + subtitles. MCP server for Claude Desktop / DSH / Cursor. 让大模型看懂视频与动图。

Let AI agents record the Windows screen, watch it as frames, and edit it with ffmpeg

MCP server: let AI assistants read your car via ELM327 - DTCs, live data, freeze frame, VIN. Mock vehicle included, no hardware needed.

Open-source MCP connector for Claude: give Claude ears for your screen recordings. Synchronized speech transcript + frames + mouse-pointer position. Local and fast.

MCP server that gives Claude Code the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends

Always-warm iOS Simulator and Android emulator frames: agents read the screen in ~20ms instead of waiting on screenshots. MCP server + CLI.

Lift the dome. Present the shot. Agent-neutral desktop capture with polished frames and stable JSON for shells and AI agents.

Store-ready App Store & Google Play screenshots from any MCP client. Device frames, benefit-driven headlines, exact store dimensions. No API keys.

Open-source MCP for Instagram Reel, post and carousel evidence: captions, speech and visual frames for AI assistants (limited unofficial beta)

Universal MCP server that gives AI assistants the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends

Local browser control and temporal visual evidence for AI agents — an MCP server that drives Chrome, continuously records it, and answers what-happened questions from retained frames, storyboards, filmstrips, and browser events

Figma design-to-code MCP server for extracting design tokens, frame layouts, component trees, and CSS styling.

Always-warm iOS Simulator frames for coding agents — read the screen in ~20ms instead of waiting on a screenshot. MCP server + CLI.

Let any coding agent watch a video: local scenes, transcript and frames, with every answer pinned to a timestamp.

Motion perception for AI agents: see and measure video, animation and synthetic scenes as labelled frames and real numbers. CLI, MCP server and TypeScript library.

Let Claude watch videos: timestamped transcript, scene-selected keyframes, exact frames and OCR. Local, no API keys. MCP server + skill + Claude Code plugin.

MCP server that gives AI agents full read & write access to Figma — 50+ tools for creating frames, placing components, styling, auto layout, and more.

Engine-agnostic fighting game character authoring tool: JSON-on-disk project format, frame/state editing, export adapters, plus an MCP server (SvelteKit + Tauri + Rust).

Native in-process MCP server for Godot: AI agents edit scenes undo-safely, play the game, inject input, capture frames, and debug.

MCP fetch server with correct SSRF defense: resolve once, validate and pin the resolved IP, re-check every redirect. Returns clean markdown framed as untrusted data.

Screenshot a URL at device viewports, optionally framed in device bezels, signed in or not, and audit it before launch. CLI and MCP server for AI coding agents.