Image, audio and video generation and processing.
🎯 ENHANCED AI GUIDANCE v4.1.2: Dramatically improved tool descriptions help AI users choose the right tools instead of 'close enough' options. Ultra-fast keyboard automation (10x speed), universal recording, multi-ecosystem debugging support, and compreh
MCP server that gives coding agents a real design system (DESIGN.md) for frontend work - searches getdesign.md, designmd.app and designmd.ai, and returns only the slice you asked for.
MCP server that gives any text-only LLM vision — image analysis, OCR, comparison, region zoom, and video frame analysis.
MCP Server / WorkBuddy CLI for Sora AI Video Generator (1.0.12 with browser-based OAuth).
MCP server that bridges Instant Design (js.design) plugin to Cursor/Claude for design-to-code
OpenClaw plugin for ElevenLabs voice agent — outbound AI phone calls with context-aware prompting and transcript processing
Artemis MCP server and CLI — let Claude Code, Codex and Ares post design decisions for a human to review and hear the verdict back. Agents post and read; only people decide.
Local-first MCP server for video and image editing — ffmpeg and ImageMagick driven by natural language. 100% offline: no keys, no network calls, no uploads, no account.
MCP server that gives AI tools the UI Explorer library: 18 design styles, 36 components with copy-ready HTML/CSS/Tailwind, and 24 animations.
MCP server for architecture and system design. Store and manage project architecture locally.
MCP server that engraves GNU LilyPond sources into cropped EPS, PDF, SVG, and PNG assets
MCP server (stdio) exposing 145+ NVIDIA NIM models - chat, embed, rerank, VLM, Flux image gen, OCR, safety. Bun-native, Codex/Claude/opencode-ready.
Author, validate, edit, and render deterministic .zen design docs to PNG/PDF.
MCP server for ReelScribe video transcription - transcribe Instagram, TikTok, YouTube, and Facebook videos from any AI assistant
OBSIDIAN FLOW MCP — The Official Video Production MCP Server & Deterministic Cinema Engine. Made by real filmmakers, driven by AI agents. Owned by you. Forged in volcanic fire.
Competitor research for AI agents: real competitor pages, side by side on one slide and deck.
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
Your agent said done. It never watched it run. caught-in-4k turns UI recordings into frames an agent can see: what changed, what flickered, what never moved. CLI, MCP server and agent skill.
Official MCP server for podkst.ai: generate AI podcasts (two-host dialogue, monologue, script-to-audio) from any MCP client over stdio.
AI image, video, and audio generation for MCP — one API key, every model, wiring never changes.