Design & Media MCP Servers for OpenAI Agents SDK

Multi-track MIDI MCP server for vibe composing music

MCP server for generating images and short videos via Google's Gemini API (Imagen 4 and Veo 3.1), for use inside Claude Code.

This project is a Model Context Protocol (MCP) server that converts image files to WebP format.

MCP server for WhatFontIs — identify fonts from images inside Claude Desktop, Claude Code, Cursor, and any other MCP-compatible AI client.

MCP server for the XBrush AI media generation API (image, video, TTS, music, sound effects, lip-sync & talking photos, video extend/retake

MCP Server for generating Xiaohongshu content outlines and images

YouTube tools for AI coding agents — search, transcripts, video info, channel browsing, playlists

MCP server for downloading YouTube transcripts using Supadata API

MCP server for 4o-image API integration - Generate images using text prompts and edit existing images

MCP server for AI-powered icon search and generation - integrates with Claude Desktop

MCP server for generating ASCII art from images - Convert images to text or PNG ASCII art with multiple character sets and color modes

MCP server for audio plugin development — load VST3/AU/CLAP plugins, process audio, render MIDI, analyze spectral content, and compile JUCE

MCP server for AutoEQ headphone equalization database — search, compare, and get EQ settings for 8800+ headphones

Generate beautiful, presentation-ready charts (SVG + PNG). Supports 14+ chart types.

Python library and MCP server for controlling Novation Circuit Tracks via MIDI

Clipboard-first MCP server that gives vision-less LLMs image recognition via OpenAI-compatible vision models.

MCP server for vision analysis through ChatGPT/Codex OAuth credentials

MCP server for ComfyUI workflow automation by IO-AtelierTech

DeepSRT MCP Server - YouTube video summarization and transcript extraction

Figma MCP server for AI coding agents — fetches and simplifies Figma design data with image optimization tweaks.

CLI and MCP server for Figma — read files, components, styles, and more from your terminal or AI agent.