Media

An MCP server for prompt optimization in Claude Code

MCP server for FlowSpeech — context-aware text-to-speech with emotion control, pause control, and 30+ voices

Dual-mode MCP server for SeaMeet — let AI agents (Claude Code, Codex, Cursor) drive the desktop recorder when it's running, else read your synced cloud library and manage webhooks. Cloud mode authorizes by logging into the web app — no key copy/paste.

本地MCP服务，为开发Agent提供TTS语音播报能力（支持播报提示音）

Vision Bridge MCP Server — 让 DeepSeek（纯文本模型）通过 MCP 调用视觉模型来「看到」图片。支持 SiliconFlow / OpenAI 兼容 API，含图片压缩功能。

MCP server that gives AI apps (Claude, Cursor, VS Code Copilot, Windsurf) full CREATE/EDIT/DELETE control over Figma via Chrome DevTools Protocol. The only Figma MCP that can modify designs. Now with comment reading/posting. No plugin — just npx tellfigma

A pluggable, AI-native drag-and-drop website builder for React — pick your design system (shadcn, MUI, plain HTML), drop the editor in, and let humans or AI agents (via the built-in MCP server) build designs.

MCP server for AI filmmaking — shot analysis, model comparison, prompt engineering, production estimation, and character consistency guidance powered by NerdFX AI

MCP server for extracting YouTube video subtitles as clean text

Perceptron MCP server for high-accuracy visual perception powered by fast, efficient vision-language models

Product design skills MCP server - structured design workflow tools for AI agents

Lightweight multi-channel MCP server for vision understanding and OCR. Integrates multi-provider failover, transient retry, and clarity-first image compression. stdio + Streamable HTTP transports.

MCP Server for image generation using Replicate's flux-schnell model

MCP server for AI-powered image and video analysis - supports OpenAI, Claude, and multimodal vision APIs with local file and URL processing

Screenshot capture, AI analysis, OCR, visual regression testing, token compression — headless server + MCP tools for AI coding CLIs

Persistent memory for visual intelligence. MCP server for the Phototology registry: analyze photos with composable lenses, enrich files with EXIF/IPTC/XMP metadata, and look up cached results for free. Works with local files. Analyze once. Remember foreve

MCP server for Figma design platform - lets AI assistants read designs, export slices and restore HTML+CSS.

MCP server: fetch YouTube transcripts, search for moments by keyword, return text-only summaries. Powered by youtube-transcript. Free, MIT.

MCP for Replicate Flux Model

MCP server for creating and editing images using Google's Gemini 2.5 Flash Image model (nanobanana)