"Papers With Code" matching MCP servers:

Enables an AI agent to make music with SuperCollider by rendering code to WAV files offline with peak and RMS level stats, plus realtime playback and stopping. Runs on macOS and Linux via a subprocess, with per-call process isolation so crashes or hangs can't take the server down.

Makes Claude a real operator for Adobe Premiere Pro 2025, providing 59 tools to control projects, timelines, media, exports, and even create cinematic intros with beat detection and style presets.

Enables deterministic room acoustics analysis through MCP tools that compute axial, tangential, and oblique standing wave modes, Bonello and Bolt criteria compliance, Schroeder cutoff frequency, and Sabine/Norris-Eyring RT60 decay across octave bands for rectangular rooms. Also derives optimal speaker and sweet-spot coordinates with SBIR notch predictions and calculates the acoustic treatment area needed to hit target reverb times for podcast, mixing, home theater, or listening use.

MCP server that brings ElevenLabs to Claude Code — text-to-speech, sound effects, music generation, voice cloning, speech-to-speech, transcription, and voice isolation. 8 tools for industry-leading AI audio.

Enables Claude Code to transcribe audio and video files using the Speechmatics Batch API, with support for speaker diarization, batch processing, and searching transcripts.

MCP server for Spotify that lets AI agents search music, control playback, and manage playlists via the Spotify Web API.

Connects any MCP-compatible AI assistant to Audacity, providing 132 tools for real-time audio editing, cleanup, mastering, and transcription — all running locally without cloud dependencies.

Exposes podcast ingestion operations (listing, downloading, transcribing, summarizing, and searching) as MCP tools, with both stdio and HTTP transport, supporting multiple podcasts via configuration.

Provides audio feedback by playing sound effects when Cursor AI completes code generation, creating a more interactive coding experience.

A local stdio MCP server that lets an Agent use configured multimodal providers to inspect images, video, audio, and music files, acting as a sensory layer for text-only LLMs.

Enables AI clients to turn text into synthesized speech through a remotely hosted GPT-SoVITS model, returning a signed, time-limited audio link that can be played or downloaded. Supports Chinese and English text with your own reference audio for voice and tone.

Enables agents to synthesize Chinese speech with Edge-TTS or offline Piper and generate engine-level timestamp SRT subtitles, including batch parallel synthesis and voice presets.

Enables chat-driven audio analysis and enhancement using local Claude, including denoising, EQ, compression, and loudness normalization, with an A/B viewer for synchronized comparison.

Model Context Protocol (MCP) server for SuperCollider integration with Claude Code and other MCP clients.

MCP server that wraps Daniel M Karlsson's SuperClean SC pattern engine, enabling control of Pdefs, tempo, and hushing via Claude Code through an OSC bridge.

Enables local, CPU-only audio post-production through tools for denoising, LUFS loudness normalization, silence removal, format conversion, pitch shifting, and speed changes. Supports podcast and video platform loudness compliance workflows.

MCP server + web dashboard for TouchDesigner. Inspect, optimize, and control TD patches from Claude Code or the browser.

Enables AI to transcribe Japanese talk videos, edit subtitles with filler removal and timing correction, and export SRT files using local Whisper models.

Enables Claude Code to control Ableton Live directly through a Max for Live device, letting users read set state, search samples, place clips, build Drum Racks, adjust device parameters, and generate .als project files from sample packs without launching Live.

Bridges MCP clients to a running SuperCollider IDE, enabling code evaluation, state queries, post window capture, and screenshots via OSC.