Entertainment and Media Servers

Parse and manipulate MIDI files based on Tone.js

Provides cryptographically secure dice rolling with standard notation and Fate/Fudge dice support for tabletop RPGs and games requiring reliable random number generation.

Integrates with The Movie Database (TMDb) API to provide TV show discovery, recommendations, and streaming information based on genres, trends, and viewer preferences.

Integrates with Ticketmaster's Discovery API to search and retrieve detailed event, venue, and attraction data for entertainment planning and ticketing assistance.

Integrates with Google Maps to create virtual travel experiences where users can navigate real-world routes with customizable avatars, discover nearby facilities, and share journeys on Bluesky.

HeyGen

Official

Enables AI avatar video generation through HeyGen's API with tools for retrieving voices and avatars, creating videos, and checking generation status.

Provides direct control over Strudel.cc for live coding music generation through browser automation, offering 40+ tools for pattern creation, music theory operations, genre-specific generators, and real-time audio analysis with session management.

Integrates with Steam's API to fetch and analyze game reviews and information, enabling customizable queries for player feedback, sentiment tracking, and game details.

Integrates with Placid's API to generate dynamic images from templates for tasks like social media posts and marketing materials.

Fetches web content and YouTube video transcripts, converting HTML to Markdown and extracting timestamps for reference in conversations.

MiniMax Multimodal

Official

Official JavaScript implementation that integrates with MiniMax's multimodal capabilities for image generation, video creation, text-to-speech, and voice cloning across multiple transport modes.

Integrates with The Guardian's Open Platform API to search articles, retrieve full content, browse sections, and perform analytical operations like author profiling and topic trend analysis with 17 specialized tools including Long Read discovery and content timeline analysis.

Integrates with Spotify Web API to enable music search, playback control, and playlist management for applications needing music data and content access.

Integrates with OpenAI's DALL-E 3 API to generate high-quality images with configurable size, quality, and style parameters, automatically saving results locally with descriptive filenames.

Enables high-quality voice generation from text using OpenAI's TTS API with customizable voices, formats, and speech parameters for seamless audio playback during conversations.

Provides quick access to Evan You's v-rapper video from VueConf 2025 through a single tool that returns the Bilibili video URL when queried about the rap performance.

Integrates with YouTube Data API to retrieve and analyze video content, transcripts, channel statistics, and engagement metrics across different regions and categories without leaving the conversation interface.

Integrates with VOICEPEAK engine to generate natural-sounding Japanese speech with customizable narrators, emotions, speed, and pitch parameters for voice content creation and language learning applications.

Allows AI models to search, retrieve, and utilize GIFs from Giphy.

Text-to-speech server that converts text into spoken audio through Rime's API, streaming with optimized buffering for minimal latency between generation and playback.

Enables playing chess against language models through a visual interface with tools for board visualization, move execution, game initialization, and position analysis from PGN notation.