Skip to main content
Glama
123,494 servers. Updated
20 Best GitHub MCP Servers: compared and ranked, November 2026Ranked from 2,309 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"How to list a remote MCP server on GitHub's MCP directory" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    C
    maintenance
    Connects to LibTV's canvas and media platform to create and edit canvases and nodes, generate images, videos, audio and speech, manage screenplays and storyboards, and run timeline edits and exports. Authorization happens once via a WeChat QR scan using OAuth 2.1 with PKCE, after which tokens are stored locally and refreshed automatically.
    365 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP clients such as Claude to generate spoken audio locally, narrating English with Kokoro and Malayalam with IndicF5, Parler-TTS, Piper or MMS, including cloned Malayalam voices, pronunciation lexicons, and number/currency expansion. Outputs loudness-normalised WAV or MP3 and runs long narrations through a pollable job queue so tool calls never time out.
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP clients to measure a track's loudness and peak levels, strip artifacts left by AI generators, compare mastering presets, and master single tracks or batches to streaming targets via a hosted remote server or a local stdio bridge. Tracks are supplied as public HTTPS links, with analysis, cleanup and previews free and full masters limited by a daily free quota or credits.
    9
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables Claude to turn a described beat into a loopclub deep link for auditioning and renting on-chain by encoding track specs into a ?jam= URL and returning an ASCII grid. It also supplies vocabulary, genre examples, and a jam prompt to help generate idiomatic loops.
    2
    15 npm
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP clients such as Claude Code, Cursor, and VS Code to generate speech through three MiMo TTS models: nine built-in voices (with singing and style/audio tags), voices designed purely from a text description, and voices cloned from a local mp3/wav sample. Audio is streamed and written only inside a sandboxed output directory, with non-overwriting filenames.
    4
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables any MCP client to start, poll, and stop microphone recordings from within a conversation, returning the accumulating transcript on demand. All transcription runs locally on-device, so no audio leaves the machine.
    5
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables Claude Code to generate offline text-to-speech audio locally using Ollama speech models, play queued speech, save WAV/M4A/AIFF files, list voices, and stop playback.
    4
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables an MCP client to inspect and modify a running digital audio workstation session through a local Python remote-script TCP bridge, exposing tools for session and track structure, clip slots and MIDI notes, devices and browser items, and mixer/transport control. Read and bulk-write operations cover tempo, naming, clip creation and note editing, muting/soloing/arming, playback and scene launching, and device parameter loading and adjustment.
    32
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    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.
    4
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients to create, read, write, inspect, and validate VCV Rack 2 .vcv patch files on disk.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables Claude to check balances and model catalogs, quote costs, and generate images, videos, and audio through the Yorai API, with idempotent job creation, file upload/download, and optional remote upload links for sending media from a phone. It also supports text chat and job status tracking, running either locally or as a remote HTTPS connector.
    11
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP clients to search songs, retrieve details and lyrics, and manage personal playlists on NetEase Cloud Music, with optional local player control on macOS, all through a privacy-first, self-hosted service.
    17
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables MCP-compatible agents to split a finished song into vocals, drums, bass, and other stems using local Demucs or a remote command, with asynchronous job status and cancellation.
    4
    AGPL 3.0
  • A
    license
    A
    quality
    C
    maintenance
    Gemini Audio MCP is a high-performance Model Context Protocol (MCP) server that leverages the power of the Gemini 2.0 Multimodal Live API to generate high-fidelity, environmental soundscapes on-demand.
    9
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Lets MCP clients such as Claude list, read, search and compare transcripts of Apple Voice Memos on macOS, keeping word-level confidence marks so uncertain words stay visibly flagged. Adds speaker separation, optional local voiceprint recognition, and independent second-reader comparisons that highlight where two engines disagreed.
    10
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables MCP clients such as Claude Code to control Ableton Live 12.1+ through a stdlib-only Remote Script, covering tracks, Drum Rack kits, MIDI clips, playback, and undo, with offline .mid export when Live is closed.
    27
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    Enables text-to-speech functionality on macOS using the say command, offering extensive control over speech parameters like voice, rate, volume, and pitch for a customizable auditory experience.
    2
    12 npm
    20
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables MCP clients to manage a local Cubase instance in the background via MIDI Remote, covering project lifecycle, MIDI/audio import, track, plugin, automation, and routing edits, transport control, and non-UI audio export.
    53
    1
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    Enables an MCP-capable app to search, play and control the YouTube Music session the user is already signed in to in their own browser — playing songs or saved playlists, choosing from a full result list, skipping and pausing playback, and reading what is currently playing — with no API keys, separate profile or screenshots.
    8
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables an agent to DJ in FUSER by searching songs, dropping discs on the decks, and changing key and tempo through a mod running inside the game.
    20
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Local Python MCP server for inspecting and automating Ableton Live Sets, including MIDI editing, device control, audio analysis and groove tools. Connects MCP clients to a MIDI Remote Script and extension bridge on the user’s machine.
    97
    4
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets AI agents search, read and export call recordings, transcripts and AI meeting notes from Digisensus Recorder, a free open-source call recorder for macOS, and start or stop recording. Runs locally on the Mac and talks to the app over a Unix socket.
    19
    GPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables agents to speak text and read documents aloud on the user's computer, with tools for speaking, reading, stopping playback, and saving audio.
    GPL 3.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables ChatGPT, Claude, Cursor, VS Code and other MCP clients to create and edit AI images, videos, songs and voiceovers from plain-language requests, including background removal, upscaling, and effect videos. Connects as a hosted remote server with OAuth 2.1 or API key sign-in, quotes credit prices before generating, and returns results directly in the chat.
    1
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets AI assistants control a NUX MG-30 guitar processor over USB MIDI by picking amp, cab, drive, modulation, delay and reverb models, toggling blocks, and setting knobs by name. It can also read, save, rename, back up and restore presets on the device, and apply whole tone recipes from JSON patch files.
    57 PyPI
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables UI-first automation and inspection of FL Studio on Windows, using actual GUI input and UIA or screenshot-confirmed targets to create and edit musical elements, with read-only bridge and FLP verification. It supports tested Piano Roll, Playlist, Sytrus, and Mixer workflows while failing safely on unknown layouts.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables a coding agent to operate an Elektron Analog Rytm MKII through semantic MCP tools, with validation-first safety, snapshots, and rollback for persistent changes.
    3
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    A fully local stdio MCP server that lets AI agents run FFmpeg operations on media files without cloud uploads or API keys. It enables probing media metadata, trimming silence, reframing video to 1080x1920 vertical format, burning in .srt subtitles, and normalizing loudness to -14 LUFS.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to listen to audio files on the local machine by transcribing speech offline with Whisper, analyzing music and sound (tempo, pitch, melody, key, loudness), and rendering spectrogram images that vision-capable models can inspect.
    1
    MIT