Design & Media MCP Servers

MCP server that gives Claude Code the ability to take screenshots. Capture full screen or specific windows by title. Windows only.

MCP server for SnapiX - image optimization, conversion, generation, and gallery management via the Model Context Protocol

Intelligent MCP server for Google Stitch — design systems, accessibility, responsive, framework conversion

MCP server: public widgets (no key) + full Studio MCP (images, media, brands, canvases, assets, series, workflows) via STORYKIT_API_KEY.

Model Context Protocol server for swatchbook — exposes a DTCG project's tokens, axes, and diagnostics to AI agents without running

Reads text aloud locally on Windows, macOS, and Linux. No API key, account, or cloud service.

MCP server implementing image compression using the TinyPNG API, supporting single and batch image compression with detailed compression sta

MCP server for TinyPNG

Setup CLI for Tubask — hosted YouTube MCP for Claude, Cursor, and ChatGPT. Search, summarize, and quote videos in chat with 3 tools.

MCP server for UIcockpit, the design system generator for AI-built apps: an agent generates a kit from a brief, reads its tokens +

MCP server for vidhook — generate videos from JSON through the vidhook render API (validate, render, get_status).

Deterministic vocal instrument engine — additive synthesis with formant control

MCP server exposing Yandex Vision OCR (printed, handwritten, tables, markdown, math) for images and PDFs as tools for LLM clients.

Production-grade MCP server that lets LLM agents inspect, plan, download, and postprocess media URLs with yt-dlp, including YouTube and

MCP Server to extract transcript from a YouTube video

Zvid: render videos & images from JSON; manage templates, projects, webhooks & credits.

Automate Blender workflows with external Python control, background operation, and LLM integration

An MCP server that gives a voice to LLMs

AI video clipping with ClipMaster (clipmaster.app): clips, exports, scheduling.

AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.

Generate and evaluate academic diagrams and plots with independent model connections.