"Construct 3" matching MCP servers:

Enables sandbox-less frontends such as mobile apps to reach the WeRead official gateway over Streamable HTTP by supplying only a URL and an access token, with no local process required. Exposes 14 read-only tools covering search, shelf, notebooks, reading progress and statistics, highlights, public reviews, and recommendations, plus a token-protected dashboard for shelf, notes, and shared-reading annotations.

为小智AI音响提供音乐搜索、播放控制、音量调节和播放列表管理，支持通过语音或文字交互。

通过 MCP 协议让 AI 操控网易云音乐，实现一起听、搜歌、点歌、切歌、发私信和查歌单等功能。

An MCP server providing access to Sveriges Radio's P3 channel music playlists, including real-time tracks and historical data. It enables AI assistants to fetch current songs and search the last 90 days of playlist history by date or artist.

Enables AI assistants to interact with the M-Team private torrent tracker API for searching resources, retrieving torrent details, and downloading torrent files. It provides a bridge for Model Context Protocol clients to manage and access private tracker content through natural language.

Enables an AI assistant to construct Garry's Mod builds from props based on text descriptions or reference photos, and save them as Advanced Duplicator 2 dupes. Supports searching models, reading dimensions, setting positions, angles, colors and welds, validating builds against a server prop allowlist before writing revision 4/5 files.

Give AI agents and LLMs access to podcast data from Rephonic — covering 3+ million podcasts with listener estimates, demographics, contact details, chart rankings, episodes, and more.

Plays Spotify tracks or system sounds as notifications when Claude Code completes tasks, with desktop notifications and cross-platform support for macOS, Linux, and Windows.

A Model Context Protocol server that analyzes YouTube videos, enabling users to extract transcripts, generate summaries, and query video content using Gemini AI.

A music MCP server enabling multi-agent collaboration where AI agents jam together in real-time, with 20 tools, conductor mode, and zero dependencies.

Enables AI models to search, retrieve, and analyze YouTube videos, channels, playlists, and transcripts via the YouTube Data API, with automatic API key failover.

Exposes TeamSpeak 3 channel management as MCP tools, allowing users to list, create, update, and delete channels via natural language.

Enables control of Amazon Music playback through Claude Desktop via the Model Context Protocol. Users can play, pause, skip tracks, and search for music using natural language commands powered by browser automation.

An MCP server for Pangolin BEYOND laser software, providing 117 tools across 20 categories for AI-driven control of laser shows via OSC, including cues, zones, brightness, BPM, and more.

Enables AI clients on a trusted LAN to search series, resolve episode and lock status, submit up to 500 episode downloads to a configured shared directory, and check, stop, or retry download tasks without API tokens.

Hosted MCP server that lets Claude, ChatGPT, Perplexity, Cursor and other AI assistants download videos as MP4 or audio as MP3/M4A from YouTube, TikTok, Instagram, Facebook, Vimeo, Twitch, SoundCloud and 6 more platforms. No install; free for 3 downloads a day.

Enables video generation from text prompts or images using Google's Veo 3 API. Supports multiple models, audio generation, and various aspect ratios for creating high-quality videos.

Provides read-only access to Bilibili through 25 MCP tools for videos, subtitles, danmaku, comments, Opus, user profiles, feeds, public favorites, video collections, live rooms, public crew lists, images, and video frame capture. Supports single-account QR-code login and Docker Compose deployment.

A Magic 8 Ball MCP server that wraps StupidAPIs to answer yes-or-no questions with mystical responses, supporting cynical and corporate modes.

Enables AI agents to search and filter titles, browse rankings, read comments, manage favorites, download albums, chapters, and covers with live progress, cancellation, and retry, and convert downloads into ZIP, PDF, or long images, all through natural language. Exposes 21 tools and 3 knowledge resources over stdio, SSE, and HTTP transports, along with runtime configuration and account login.