MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
thadm-mcpupdated this year
MCP server for thadm - search your screen recordings and audio transcriptions
npm MIT -
radiq-mcpactive
MCP server for radiq - search your screen recordings and audio transcriptions
npm SEE LICENSE IN LICENSE.md -
screenpipe-mcpactive
MCP server for screenpipe - search your screen recordings and audio transcriptions
npm SEE LICENSE IN LICENSE.md -
@zoen-app/mcpgithub.com/enzotironi/zoenappupdated this year
MCP server for zoen - search your screen recordings and audio transcriptions
npm MIT -
Emilia – Adaptive music, podcast, streaming and audio recorder/player for Linux with MCP
GPL-3.0 ★ 2 -
Desktop microphone recorder with real-time, on-device transcription, automatic audio segmentation, voice activity detection, and an MCP server for searching saved transcripts.
★ 431 -
AbhiMeetgithub.com/abhishekjoshi-eng/AbhiMeetupdated this year
Free open-source meeting recorder with AI transcription & reporting. Fireflies.ai alternative. Records audio + screen, transcribes with Whisper AI in 90+ languages, generates meeting minutes via Claude MCP. No subscription, 100% local.
MIT ★ 1 -
paste-audio-mcpupdated this year
MCP server for paste.audio — hand Claude a voice memo or recording, get a clean transcript back. No account, no API key.
npm MIT -
claude-meeting-mcpgithub.com/Aedelon/claude-meeting-mcpupdated this year
MCP Server to record, transcribe, and summarize any audio — meetings, YouTube, podcasts, lectures — with speaker identification and automatic meeting minutes. Cross-platform (macOS, Windows, Linux).
Apache-2.0 ★ 1 -
Screenshots, screen recording, wallpaper, audio routing MCP
GPL-3.0 -
devstudio-mcpstale
Production-grade MCP server for screen recording, audio capture, and demo automation
pypi AGPL-3.0-or-later -
MCP server for LeiUtils: transcribe local audio/video files into a workspace matter, fetch and search the transcript, and record and discuss evidence from it.
npm Apache-2.0 -
recordergithub.com/jaenster/recorderupdated this year
macOS menu-bar app that records mic + a specific app's audio in stereo, transcribes on-device via SpeechAnalyzer, summarizes with Apple Intelligence, and exposes recordings to Claude via MCP.
MIT -
MCP server for BlueColumn — persistent semantic memory API for AI agents. Remember, recall, and store observations across sessions. Audio Intelligence (calls, sound events, music) plus Music Memory: store practice recordings and lessons with instrument/ke
npm MIT -
Let Claude listen to audio and watch video: transcribe voice messages, podcasts and recordings (word timestamps, 99 languages), and summarize or edit TikTok, YouTube & Instagram links. MCP server for Claude Desktop & Claude Code. Runs locally.
pypi MIT ★ 1 -
AI production assistant for OBS Studio. 168 MCP tools, scene workflows, previews, audio, recording, timed cues and validated OBS API access.
MIT ★ 1 -
Self-hosted, multi-user transcription platform: record or upload audio. Speaker-labeled, timestamped transcripts, Recognize speakers across recordings, Summarize, extract action items and chat over your transcripts with your own OpenAI-compatible LLM. Your Audio, your Server, your Model. Tested: Laptop RTX4070, RTX3090, RTX5090 and ROCM Strix Halo
npm AGPL-3.0 ★ 9 -
plaud-mcpgithub.com/charathram/plaud-mcpupdated this year
MCP server for Plaud.ai — access audio recordings, transcripts, and summaries
npm MIT -
Self-hosted meeting recorder: records your mic and system audio separately, transcribes locally with Whisper, and writes AI meeting notes. Windows/macOS client, Docker server, Notion export, REST + MCP for AI agents.
MIT -
A local MCP server that lets Claude Desktop transcribe audio with MacWhisper or whisper.cpp—keeping recordings and transcripts on your Mac.
pypi MIT ★ 3 -
AI-powered stream and recording control for OBS Studio via MCP — 148 tools for scenes, audio mixer, filters, streaming, recording, and stream health diagnostics.
Apache-2.0 ★ 28 -
Local MCP server that turns screen recordings and video URLs into keyframes, OCR, audio transcripts, and timelines for Claude Code. Watch a YouTube tutorial, search past sessions, long-poll for screen changes.
MIT -
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, manage webhooks, and upload local audio/video files for transcription. Cloud mode authorizes b
npm MIT -
Production-grade MCP server for professional screen recording and demo automation. Features multi-monitor support, audio/video muxing, and seamless integration for AI-driven workflows.
NOASSERTION ★ 6 -
Screen recorder for Windows that Claude can drive. Built-in MCP server lets an AI start/stop recordings, see screenshots, review frames, cut clips, extract audio and send files over Wi-Fi. Sharp native-resolution capture, region select, built-in editor, LAN sharing.
NOASSERTION -
Python CLI and MCP server for Plaud recordings — bring transcripts, summaries, and audio into your AI assistant.
pypi NOASSERTION ★ 1 -
obs-studio-mcpgithub.com/aaronckj/obs-studio-mcpupdated this year
MCP server for controlling OBS Studio over obs-websocket v5: scenes, sources, audio, streaming, recording, replay buffer, stats, and text overlays.
pypi MIT -
obs-mcpupdated this year
MCP server for AI-driven OBS Studio control via obs-websocket v5 — scenes, sources, filters, audio mixer, streaming, recording, and studio mode.
pypi Apache-2.0 -
vibe-code-granolagithub.com/alnutile/vibe-code-granolaupdated this year
Amble — a local-first meeting recorder and AI notepad for macOS. Records system audio + mic, transcribes with whisper.cpp on-device, writes structured notes, and exposes your meetings to Claude over MCP. Built with Tauri 2.
MIT ★ 4 -
Local-first meeting capture and transcription for Claude Code — records meeting audio via macOS ScreenCaptureKit, transcribes locally with whisper.cpp, no data leaves your machine
Apache-2.0 ★ 1 -
stt_mcpgithub.com/AuraFriday/stt_mcpupdated this year
This STT (Speech-to-Text) MCP tool enables AI agents to receive voice input from users via microphone recording or audio file transcription. It's the companion to the TTS tool, enabling full bidirectional voice communication between AI and users.
Apache-2.0 ★ 1 -
ableton-copilot-mcpgithub.com/xiaolaa2/ableton-copilot-mcpupdated this year
An MCP server built on ableton-js enables AI assistants to control Ableton Live in real time, including Arrangement View operations such as song management, track control, MIDI editing, and audio recording, along with other capabilities.
npm MIT ★ 94 -
Siljangnim for MCP agents: a creative coding studio your agent drives — make live visuals by talking, change and mix them, perform with MIDI/OSC/audio, record video
npm GPL-3.0-or-later -
Private, local audio & video transcription with Whisper: live meeting recording with who-spoke, summaries, minutes and an MCP server for Claude/Copilot. Linux · Windows · macOS · EN/ES
Apache-2.0 -
MCP server for Equalang: translate PDF, DOCX, PPTX, XLSX, EPUB, subtitles, pictures, audio and video with the layout kept; transcribe recordings.
npm Apache-2.0 ★ 22 -
Collects research material from web pages, papers, APIs, PDFs, scans, audio and video into a local corpus where every item records its source, method and hash.
pypi AGPL-3.0 ★ 6 -
@verifyapi/mcp-serverupdated this year
MCP server for FirstHandAPI — human-in-the-loop crowdsourced data collection. Claude Code + Cursor integration for collecting photos, video, audio, screen recordings from real humans with AI quality scoring.
npm -
MCP server for FirstHandAPI — human-in-the-loop crowdsourced data collection. Claude Code + Cursor integration for collecting photos, video, audio, screen recordings from real humans with AI quality scoring.
npm MIT -
Eyes, ears and hands for AI agents on GUI programs: a sealed X11 or Wayland session where an agent (over MCP), a script or CI reads the accessibility tree, takes screenshots, records video and sound, clicks, types and drives gamepads, then checks contrast, Tab order, visual diffs, flicker, input latency and audio dropouts. CLI, Python, Playwright.
npm MIT ★ 2 -
A private multilingual recording archive.
MIT -
audio-mcpgithub.com/BugorBN/audio-mcpupdated this year
Local MCP server for macOS that captures mic + system audio into explicit sessions and exposes raw WAV audio to AI agents
MIT ★ 7 -
audio-mcpupdated this year
Local MCP server for macOS that captures microphone + system audio into explicit sessions and exposes raw WAV audio (stereo L=mic, R=system) to AI agents.
npm MIT -
Local-first Plaud Note Pro audio vault. Direct Bluetooth imports, Mistral/Voxtral transcription, Markdown documents, AI chat, REST API and MCP. Tauri macOS app; experimental Android.
MIT ★ 46 -
Free, open source call recorder and bot-free AI meeting note taker for Mac: record Zoom, Meet, Teams, FaceTime, WhatsApp and phone calls, get transcripts and meeting notes.
GPL-3.0 ★ 19 -
TalkTuck for macOS — Mac 版源码:本地录音、转录、mini 悬浮窗、音源切换、分组与 Agent / MCP 集成。macOS source code for local recording and transcription.
★ 6 -
Mac menu bar meeting recorder: records calls without bots, transcribes (cloud or on-device), and makes your meetings searchable from Claude via MCP.
MIT ★ 8 -
Local MCP server to analyze video, audio & images — extract frames, transcribe speech, OCR on-screen text. Give Claude, Cursor & VS Code video context. No API keys, no cloud.
npm Apache-2.0 ★ 2 -
Thenvia · 留境 — Local-first personal context memory for your AI agent. Native macOS notch capture, grounded recall, and plugin/MCP access.
★ 3 -
MCP server that lets an AI agent act as a recording producer inside Logic Pro. Work in progress.
MIT -
MCP server for the Vox Trust protocol: verify sealed voice recordings (WAV) from any AI assistant, with the seconds that changed. Verify-only, no secrets. Pre-1.0, not audited.
npm Apache-2.0 -
Fix a voiceover mistake without re-recording: re-voice one sentence in your own voice and splice it in with matched loudness, EQ and room tone. Open-source Overdub alternative. CLI + MCP server.
pypi MIT