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.
-
—
★ 1 -
whisper-stt-mcpgithub.com/fxckcode/whisper-stt-mcpupdated this year
MCP server for local high-quality audio transcription using faster-whisper (CTranslate2) with NVIDIA GPU acceleration
-
Paste a TikTok, YouTube or Instagram link, get the spoken text: local faster-whisper on CPU, optional Claude analysis (hook, structure, why it works), MCP server for Claude Code.
MIT -
Self-hosted MCP server + REST API: turn any YouTube, Instagram, TikTok, X, Facebook or podcast link into a Whisper transcript for Claude, Cursor, OpenClaw and other AI agents. faster-whisper + yt-dlp in Docker.
MIT -
Model Context Protocol server for extracting TikTok video metadata, transcribing speech with Faster-Whisper, and automating media workflows.
MIT ★ 1 -
MCP server for audio transcription via faster-whisper (local) or OpenAI Whisper API
pypi MIT -
A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.
★ 19 -
Local RAG archive of your calls: faster-whisper transcription, pyannote diarization, entity graph and tasks, hybrid vector search with an "ask the archive" chat, live call co-pilot, Telegram and document ingestion, MCP server for Claude. Runs on your machine.
MIT ★ 2 -
simple-asr-mcpgithub.com/selentar/simple-asr-mcpupdated this year
Minimal MCP server for local speech recognition using faster-whisper
pypi MIT -
workos-meeting-mcp-servergithub.com/workos/workos-meeting-mcp-serverupdated this year
MCP server for meeting transcription & analysis — transcribe audio/video via faster-whisper, extract insights, generate notes.
pypi MIT -
Local meeting note-taker for Windows: records calls without a bot, transcribes offline (faster-whisper), writes notes with a local LLM (Ollama). Evals, tests, MCP server.
MIT -
Local AI voice for coding assistants — TTS & STT via MCP. Kokoro ONNX + faster-whisper, fully offline.
npm Apache-2.0 ★ 11 -
ai-video-editorgithub.com/timkulbaev/ai-video-editorupdated this year
CLI tool that auto-edits talking-head videos: removes silences, filler words, and restart phrases using Silero VAD + faster-whisper. MCP server for Claude Desktop included.
MIT ★ 14 -
minicpm-vision-mcpgithub.com/wjh1547485653-max/minicpm-vision-mcpupdated this year
为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器,基于 Ollama + MiniCPM-V 4.6 + faster-whisper,图片描述·视频分析·语音转文字
MIT ★ 17 -
social-knowledge-basegithub.com/guimatheus92/social-knowledge-baseupdated this year
Turn social-media creators' videos into a searchable, curated knowledge base — Next.js download/manage app + GPU transcription (faster-whisper) + RAG
MIT ★ 14 -
whisper-telegram-mcpgithub.com/abid-mahdi/whisper-telegram-mcpupdated this year
Two-way voice for Claude via Telegram — Whisper transcription + Kokoro/OpenAI TTS as an MCP server
pypi MIT ★ 1 -
An MCP server that gives an AI client a YouTube video's text: metadata, existing captions, or a local-GPU Whisper transcription.
MIT -
Local voice input/output layer for authorized MCP clients; adds speech without adding new tool privileges
Apache-2.0 ★ 2 -
Offline dictation and meeting notetaker for Windows: local Whisper transcription, speaker labels, and an MCP server for Claude Code.
MIT -
Open-source MCP connector for Claude: give Claude ears for your screen recordings. Synchronized speech transcript + frames + mouse-pointer position. Local and fast.
MIT ★ 2 -
Local-first analysis of X.com posts as an MCP server: video transcripts with Whisper, summaries and image descriptions with Gemma via Ollama. Nothing leaves your machine.
NOASSERTION -
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 -
Cut a video by deleting words from its transcript. Local Whisper transcription, retake detection, an MCP server for Claude, verified MP4 export.
MIT -
Local offline speech recognition for Russian speech with German words: ASR model ensemble with word-level voting, diarization, desktop app, CLI and MCP server. Research notes included.
GPL-3.0 -
guitar-practice-appgithub.com/BlaiseMoses01/guitar-practice-appupdated this year
A hands-free voice controlled youtube playback and metronome orchestration tool built for Claude Code
MIT ★ 1 -
Self-hosted transcription service: Whisper speech-to-text, pyannote speaker diarization and LLM meeting summaries behind an async REST API and an MCP server.
WTFPL ★ 1 -
AI-native video editor driven as a local MCP server. Linux + Windows: ingest, transcribe, edit graph, melt/ffmpeg render, QC.
MIT ★ 59 -
multimodal_search_mcp_architecturegithub.com/estelacode/multimodal_search_mcp_architectureupdated this year
Low-Latency Multimodal Search Web App with MCP Architecture 🔌🛠️🧠 #StrandsAgentSDK #FasterWhisper #Multilingual #MultimodalSearch #ChromaDB # DockerCompose
★ 1 -
🎙️ Video & audio → timestamped transcripts + clean summaries. Local Whisper on Windows, standalone Android app, Chrome extension, and MCP server for AI agents. No accounts, no cloud uploads, no per-minute bills. 📱💻🤖
MIT ★ 1 -
Self-hosted Opus Clip / Klap / Vizard alternative: turn long videos into captioned 9:16 Shorts with local Whisper, face tracking, active-speaker cuts and Remotion captions. MCP-ready, MIT.
pypi MIT ★ 11 -
Turn any video into timestamped transcripts and keyframe contact sheets for AI agents—offline, local-first, no API key required.
MIT -
Clean up talk recordings, from one video to a whole event, by hand or through your agent.
pypi MIT -
Give AI agents (Claude Code, Cursor, MCP) eyes and ears over your video library with zero cloud dependencies.
MIT ★ 1 -
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 -
Free, agent-controllable web app for creating and editing motion graphics, with a built-in template library, MCP integration, local ASR, and practical video editing tools.
MIT ★ 3 -
speech-minegithub.com/WISCLab/speech-mineupdated this year
Working towards an MCP setup that allows humans to format audio with an agent in the loop. Useful for repetitive audio formatting tasks where the content is well defined.
MIT ★ 1 -
MCP server that lets an LLM read chats, voice notes and images and draft replies, behind a tested send gate and a 15-case red-team eval.
MIT ★ 1 -
Let AI watch videos: local files or YouTube/Bilibili URLs -> timestamped transcript + keyframes + contact sheets. Offline, no API key. MCP server + CLI + agent skill.
pypi MIT ★ 12 -
A desk pet that works with Claude Code, on a 2.8" ESP32-S3 touch screen: approvals, questions, plans, chat and voice.
NOASSERTION ★ 1 -
Your WhatsApp, searchable on your computer. Optional local voice transcripts, attachment search, and a private dashboard, with scoped MCP read and send access for AI tools.
GPL-3.0 ★ 2 -
Sedjem: transcribe Egyptian Arabic–English meetings on your own computer, with speakers told apart by voice. Desktop app for Windows and Linux, plus benchmarks and notes.
AGPL-3.0 ★ 9 -
基于JoeanAmier/XHS-Downloader二次开发的小红书 MCP 阅读扩展,无需账号登陆,支持笔记读取、视频抽帧、离线转录、公开评论读取及临时媒体清理。Read-only MCP server for RedNote (Xiaohongshu) — note text, images, video frames, speech transcription and comments. No login required.
GPL-3.0 ★ 1 -
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