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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
@webixsoft/whisper-mcpactive
Official MCP server for Whisper — create zero-knowledge secret links from AI editors
npm UNLICENSED -
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 -
🐋 Whisper to your running AI:给 WorkBuddy 挂一只会传话的小鲸鱼——任务跑得正欢,点一下挂件就能补充提示,不打断、不等候。MCP Apps + Hooks + PySide6 悬浮挂件。
MIT -
kube_whisperergithub.com/vijaypranesh/kube_whispererupdated this year
Kube-Whisperer: A locally-run, AI-powered Kubernetes operator. Connects LLMs to your cluster via MCP to autonomously debug pods, deploy YAMLs, and manage infrastructure through conversational ChatOps.
-
Private, local audio and video transcription for Claude: an MCP server that runs Whisper on your computer, on the GPU or CPU, with text, SRT subtitle, or JSON output. Works with Claude Desktop, Claude Code, and claude.ai.
mcpb 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 -
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 -
客户需求调研纪要工具:录音转写(Whisper) + AI 生成需求调研纪要 + 导出 md/html/pdf/docx,支持 Web/MCP/CLI 三种接入方式
★ 1 -
Turn a video into context an AI agent can use: a local timestamped transcript (whisper.cpp or mlx-whisper), key frames (ffmpeg) and an MCP server to search and read them.
npm MIT -
Local desktop studio for Whisper AI speech transcription, subtitle translation, OCR masking, and FFmpeg burning
MIT ★ 1 -
FastAPI/HTMX frontend for an AI Finance Agent powered by Google Gemini and Whisper voice transcription. Features file upload processing and backend tool execution using MCP
★ 1 -
Live interview checklist for macOS by Darlison Holdings: local Whisper transcription, Jev checkmarks, and MCP so any AI can run the call and add follow-ups.
MIT ★ 2 -
Record your screen while you talk. Transcribed on your Mac with whisper.cpp. Readable by AI agents over MCP.
MIT ★ 6 -
Personal AI assistant hub: a local web console over Open WebUI with multiple personas, Gmail and news briefings, voice dictation (Whisper), and Agent051 integration via MCP.
MIT -
Self-hosted YouTube downloader and player with automatic subscriptions, local Whisper transcripts, and AI research over MCP.
AGPL-3.0 ★ 1 -
Turns podcasts and videos into material your AI can work with: transcripts, podcast packages, local Whisper, MCP for Claude, Codex and open models. Self-hosted.
AGPL-3.0 -
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 -
🎙️ 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 -
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 -
levitygithub.com/A-Guidry/levityupdated this year
Local-first, cross-platform voice for AI coding assistants — speak to Claude Desktop/Antigravity and hear replies. Two-tier TTS, hands-free yes/no + free-form Whisper input, menu-bar control. macOS/Windows/Linux, BYOK, no telemetry.
MIT -
avagithub.com/harshav167/avaupdated this year
Voice interaction MCP server for AI coding assistants - ElevenLabs, Whisper, Kokoro
MIT -
Local AI voice for coding assistants — TTS & STT via MCP. Kokoro ONNX + faster-whisper, fully offline.
npm Apache-2.0 ★ 11 -
B站也逃脱不了肥牛大人的魔爪 - my-neuro B 站插件(bilibili-tools):搜索/评论/弹幕/排行榜/三连,视频综合信息含字幕提取、Whisper 转录与 AI 总结
★ 1 -
thaleiagithub.com/ConYel/thaleiaupdated this year
The Joyful Voice AI Companion - Open-source voice AI with TTS (Kokoro) and STT (Whisper), MCP server for LLM tools
NOASSERTION -
🔌 Exposes Voice & Audio. TTS, voice cloning, audio generation, transcription. Integrates with Kokoro TTS and Whisper STT. (MEOK AI Labs)
pypi NOASSERTION ★ 1 -
Private semantic search, Whisper, OCR, and MCP agent tools on Intel Arrow Lake AI Boost NPUs for Linux
MIT ★ 5 -
🎚️ 判断一首歌是纯器乐(BGM)还是人声+伴奏 —— 不猜,把人声真的拆出来量。音源分离(UVR) + 100ms 分帧能量统计,9/9 经 whisper 独立交叉验证。一个 struct 派生 CLI/TUI/Web/MCP 四端,天生 AI-callable。
MIT -
Privacy-first AI meeting assistant for macOS — local mic + system audio, Whisper transcription, Ollama/OpenAI summaries, MCP for Claude Desktop
MIT -
Local-first meeting recorder for Mac. Whisper on-device, your AI for summaries, MCP server for Claude Desktop.
Apache-2.0 ★ 18 -
MCP server for vdl — lets Claude and other AI assistants resolve, download and transcribe (Whisper) videos via your self-hosted vdl instance
AGPL-3.0 ★ 2 -
mcp-deep-videogithub.com/littler00t/mcp-deep-videoupdated this year
MCP deep video analysis server with 14 tools: motion detection, scene cuts, heatmaps, frame diffing, Whisper transcription, and annotated frame export. Includes a Pydantic AI workout coach example. Plug into Claude Desktop or build your own video agent.
MIT ★ 2 -
Free, open source video editor for Reels, TikTok and Shorts. A CapCut alternative for Mac, Windows and Linux with local Whisper captions and AI agents over MCP.
GPL-3.0 ★ 27 -
ai-driven-multimodal-analyticsgithub.com/serhatsoysal/ai-driven-multimodal-analyticsupdated this year
Enterprise-grade Multimodal AI Gateway leveraging FastAPI, OpenAI (GPT-4o, Whisper, TTS), and MCP Server architecture. Featuring asynchronous task processing, Redis caching, and real-time AI/ML pipeline orchestration.
MIT ★ 1 -
Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用
pypi MIT ★ 3 -
Offline AI meeting notes and transcription for Linux and macOS. Open-source Google AI Edge Foresight and Granola alternative with local Gemma LLM, Whisper, RAG and MCP.
MIT ★ 4 -
Local, private AI meeting notetaker for macOS: live on-device Whisper transcription of Zoom/Meet/Teams + an MCP server so Claude Code & Cursor can search your meetings.
MIT -
JiraAIgithub.com/arunkumar1997/JiraAIupdated this year
AI-powered MCP server that converts meeting notes into JIRA epics, stories, tasks & bugs — with human approval gate, RAG-based project doc search, and Whisper meeting transcription. Built for Claude + JIRA Cloud/Server.
-
ringbackgithub.com/mohitbadwal/ringbackupdated this year
Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.
Apache-2.0 ★ 32 -
🧠 Второй мозг вашего AI-агента: userbot-парсер всей переписки Telegram, локальный Whisper для голосовых, OCR картинок через vision-модели (OpenRouter), pgvector-поиск и 15 MCP-инструментов. Claude Code / Cursor / Hermes. Ваши данные остаются у вас.
MIT ★ 2 -
Record your screen, narrate the bug, and hand your AI coding agent structured Markdown - one annotated screenshot per mark. Desktop app, CLI, and MCP server for Claude Code, Cursor, Codex, and Windsurf. On-device Whisper transcription, local-first, MIT.
npm MIT ★ 85 -
Let Claude, Codex and Cursor watch your videos and screen recordings. MCP server with timestamped storyboards, zoom and a local Whisper transcript, plus WatchRecorder, a macOS app: press ⌥⇧R, show the bug while you talk, your AI gets it.
MIT ★ 1 -
Self-hosted AI media studio on a Google Colab L4 GPU: text-to-image, image editing, text-to-video with sound, music, text-to-speech, voice cloning, image-to-3D and Whisper transcription. ComfyUI + web UI + MCP server.
AGPL-3.0 ★ 2 -
Open-source AI video editor for Windows: timeline editing, frame-exact export, on-device Whisper captions, Blender and HyperFrames motion graphics, and an AI Copilot (Claude Code, Codex, OpenAI, Gemini or any MCP agent) that can see, hear and edit your video.
MIT ★ 18 -
Private, offline speech-to-text for Linux: push-to-talk dictation into any app, meeting transcription with speaker diarization, and searchable history. Whisper, Parakeet and a local LLM on your GPU (Vulkan) or CPU. Native Omarchy and Hyprland integration, Wayland, MCP for AI agents.
GPL-3.0 ★ 2 -
Let AI agents read, search and send your personal WhatsApp messages over MCP: a Go bridge on whatsmeow and a Go MCP server with 59 tools, local voice transcription (whisper.cpp), send/read allowlists, read-only mode and a human-pace send rate limit.
MIT ★ 1 -
Multi-radio, multi-machine Linux gateway: ham/GMRS radios → Mumble, Broadcastify, Winlink, APRS, Telegram, live web UI. Visual drag-and-drop audio routing, plugin radios (TH-9800, D75 BT, KV4P, FTM-150, IC-7100, RSPduo dual SDR), distributed Moonshine + Whisper transcription pool, AI fleet manager, 95+ MCP tools.
★ 14 -
yojana-sahayak-assistantgithub.com/Subh24ai/yojana-sahayak-assistantupdated this year
Fully offline, multilingual voice AI agent that helps Indian citizens discover government welfare schemes in Hindi & English. Uses Whisper ASR, fine-tuned Qwen2.5 (QLoRA), FAISS RAG, and an MCP tool server — all designed for air-gapped deployment. Covers 2,872 schemes from myscheme.gov.in.
★ 1 -
Open-source AI video editor for Claude Code and any MCP client. Removes silence and repeated takes, edits by transcript with local whisper.cpp, adds captions, and exports to Final Cut Pro, DaVinci Resolve and Premiere Pro. CLI, MCP server and browser timeline over FFmpeg. MIT, local, no API key.
npm MIT ★ 14 -
Free, local-first meeting notes for macOS. IndexOne records your calls, transcribes them on-device with Whisper, writes structured Markdown notes into your Obsidian vault and answers questions across everything you have recorded. On-device or opt-in cloud AI, a local MCP server, E2EE sharing. Downloads, docs, release notes.
CC-BY-4.0 ★ 3 -
Let LLMs and AI agents "watch" video. Zakira.Replay turns any video source — YouTube URLs, conference recordings, course lectures, local files — into speaker-attributed transcripts (captions or local Whisper STT), frame-level OCR and structured vision (local or LLM-routed), slide-aware grouping, and timestamped JSON evidence that agents can reason over. Ships as both a CLI (`zakira-replay`) and an MCP server (`zakira-replay mcp serve`) in one .NET 10 binary.
nuget MIT -
figma-whisperergithub.com/mightymess/figma-whispererupdated this year
Design in Figma by chatting with Claude — an MCP server + plugin that gives Claude write access to your canvas
-
Windows-native MCP server for local audio transcription — GPU accelerated via Vulkan, works with Claude Desktop
NOASSERTION ★ 2 -
@powforge/forge-whisper-mcpupdated this year
Read-only MCP server that exposes an autonomous AI agent's live operational state — current tick, recent learnings, tick history, hypothesis status, Bitcoin network pulse — as queryable MCP tools. Lets any MCP-compatible agent (Claude Code, Cursor, Contin
npm MIT -
Self-hosted Telegram voice journal with local Whisper transcription and Claude analysis via MCP
MIT ★ 3 -
linkpeekgithub.com/abhinav-mittal33/linkpeekupdated this year
MCP server + Chrome extension — lets Claude understand any video link using on-device Whisper and BLIP. No API keys required.
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 -
Model Context Protocol (MCP) Server for Real-Time Lecture Audio Capture, Whisper Transcription & Structured Academic Notes
MIT ★ 1 -
@usewhisper/mcp-servergithub.com/alixus/whisperupdated this year
Model Context Protocol server for Whisper Context API - Connect Claude Desktop to your knowledge base
npm MIT -
Local voice runtime and MCP server for coding agents on macOS: one mic, many agents, queued turns, local Whisper + Kokoro.
MIT -
Model Context Protocol server for extracting TikTok video metadata, transcribing speech with Faster-Whisper, and automating media workflows.
MIT ★ 1