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 descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
mcp-voicegithub.com/zavora-ai/mcp-voiceupdated this year
Voice & Realtime MCP Server — calls, transcription, sentiment, IVR, recordings, call center analytics for AI agents
cargo Apache-2.0 -
parlat-cliupdated this year
Parlat — voice transcription SDK, CLI, and MCP server for Pro users
pypi MIT -
crush-mcp-serverupdated this year
MCP server for CRUSH the Memory — access your voice notes, transcripts, and audio from AI tools
npm MIT -
Discord Voice Transcription MCP Server
MIT -
Voice-to-Text MCP Server with CUDA-accelerated Whisper transcription
-
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 -
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 -
voice-memogithub.com/Kaiji-erig/voice-memoupdated this year
Continuous voice recording with local Whisper transcription, SQLite storage, and MCP server for Claude Code integration
-
Voice + text MCP channel between a Claude Code session and the Viber UI (https://viber.dgypx.dev). Push transcripts to Claude; send_message tool delivers text back to the UI.
npm MIT -
voice-dictation-mcpgithub.com/NimbusCG/voice-dictation-mcpupdated this year
Voice dictation for Claude Code over SSH/tmux — MCP server + Whisper transcription + channel-based multi-session support
★ 1 -
WhatsApp channel plugin for Claude Code — connect your WhatsApp to an AI agent. QR scan, voice transcription, access control, media support.
MIT ★ 18 -
Personal WhatsApp MCP for Claude, built directly on whatsmeow. Encrypted-at-rest storage, Whisper voice-note transcription, accent-insensitive Spanish search, vault-native CRM integration, send-confirmation safety.
pypi MIT ★ 7 -
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 -
Your iPhone dictations, voice notes and meeting transcripts on your computer and inside your AI agents. The computer side of Zone: MCP server, CLI, local history page, Link over iroh and color Flash.
MIT -
Kolivri AI Phone Line & Voice Call Center MCP Server (8 Languages, Inbound/Outbound Calls, Transcripts & Carrier Codes)
mcpb -
voicestudio-mcpgithub.com/aiworkmagic/voicestudioupdated this year
MCP server for Voice Studio — text-to-speech, voice cloning, voice design, transcription, and music generation as agent tools.
pypi MIT -
🔌 Exposes Voice & Audio. TTS, voice cloning, audio generation, transcription. Integrates with Kokoro TTS and Whisper STT. (MEOK AI Labs)
pypi NOASSERTION ★ 1 -
mcp-retellgithub.com/lyzetam/mcp-retellupdated this year
MCP server and LangChain tools for Retell AI (voice agents, calls, transcripts)
MIT -
Voiceover & captions MCP server for AI agents: turn a script into narration + SRT/VTT subtitles from Claude, Cursor and Codex. Voice cloning, emotion tags, transcription. Miragea voice engine.
pypi MIT -
Lightweight web app and MCP-enabled tool to generate NCERT-style lesson plans using voice or text input. Key features - Voice and text input for lesson creation - Generates multi-session lesson plans, worksheets, and resources - Export as DOCX and PDF - Local SQLite database (default) to store transcripts and lessons
-
MCP server for the Vaani Voice AI API (agents, calls, transcripts, campaigns) over local stdio
npm MIT -
CLI to run a self-hosted Dograh voice-agent platform from the terminal: agents, calls, transcripts, numbers, models, campaigns, tools, keys, and an MCP server
MIT ★ 1 -
Self-hosted Telegram voice journal with local Whisper transcription and Claude analysis via MCP
MIT ★ 3 -
Desktop microphone recorder with real-time, on-device transcription, automatic audio segmentation, voice activity detection, and an MCP server for searching saved transcripts.
★ 431 -
Voice AI for AI assistants: voice agents, TTS, transcription, dubbing, narration and call analysis through PyAI MCP and browser OAuth.
MIT -
Call2Me MCP — give your AI assistant a real phone line: AI voice calls, transcripts, live interpreter (31 languages), phone numbers.
MIT -
Generate speech, voices, and transcripts through the ElevenLabs API.
npm MIT -
Official Model Context Protocol (MCP) server for NOVA Labs — give your AI agents the ability to create voice agents, place calls, and read transcripts.
MIT -
meeting-scribegithub.com/snegireff/meeting-scribeupdated this year
Personal fork of czlonkowski/simple-meeting-scribe (MIT) — local macOS meeting transcriber: Ukrainian support, summary export (Telegram/Obsidian/email), voice enrollment, transcript search MCP tool, live subtitles.
MIT ★ 34 -
ha-addon-voiceboxgithub.com/ITSpecialist111/ha-addon-voiceboxupdated this year
Home Assistant add-on for Voicebox - local AI voice studio (TTS, voice cloning, transcription, MCP server). Includes a RAM preflight that refuses to start rather than trigger the OOM killer.
★ 1 -
google-live-translategithub.com/sergiocalvog/google-live-translateupdated this year
Apify Actor & MCP Server for real-time translation, transcription, and language detection using Google Gemini 3.5 Live Translate with emotional voice preservation.
★ 1 -
Kurdish speech tools: Sorani and Kurmanji text-to-speech and transcription, voices and plans.
npm MIT -
Blazing Videogithub.com/acstener/takes-pluginno update data
Record your Mac screen, face and voice, edit the video by its transcript, and share a link.
mcpb -
Score64 — turns music and sound into game-ready Commodore 64 SID assets. Transcription, three-voice reduction, adaptive layers, sound-effect matching, GoatTracker export and packing, checked on 6581 and 8580. Rust: egui app + CLI + MCP server.
MIT -
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 -
Stop guessing why your voice agent failed. Voker reveals the full story transcripts, failed tool calls, latency, handoffs, provider errors, and likely root causes—in one evidence-backed timeline. Explore everything in the platform or bring the context into your workflow through MCP.
-
AudioPod plugin for Claude - transcription, stem separation, voice and music tools via the AudioPod MCP server
MIT -
Local speech for Macs, Apple Silicon and Intel: text-to-speech with voice cloning and a studio voice, speech-to-text, system-wide dictation, and call recording with transcript, notes and speaker separation. Runs on-device with Metal. Daemon with an OpenAI-compatible HTTP API, a CLI and an MCP server.
Apache-2.0 ★ 1 -
WhatsApp MCP server that works again: fixes 405 connection and 403 media downloads, adds free local voice-note transcription (whisper.cpp)
MIT -
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 -
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. Supports Multilingual v2, v3, Turbo, Flash, and Scribe models.
MIT -
Open-source AI podcast generator: turn any URL, PDF, text or topic into a two-host (or panel) podcast with distinct voices, chapters, SRT/VTT transcript and RSS. CLI + MCP server + Agent Skill, voiced by Miragea.
pypi MIT -
Tapra MCP server: Tunisian Derja transcription, subtitles, voices, translation and Arabizi for Claude, Cursor, VS Code and Codex
npm MIT -
Talk to Claude from WhatsApp and let Claude manage your WhatsApp safely — enhanced whatsapp-mcp: hardened bridge, always-on agent, voice transcription, drafts-first sending, desktop dashboard
MIT -
Your personal WhatsApp in Claude Code over MCP: local SQLite mirror, local voice-note transcription, sending gated by an allowlist and a confirmation dialog (macOS)
MIT ★ 3 -
Self-hosted Docker speech API for OpenAI-compatible transcription and text-to-speech, streaming ASR, voice cloning, phoneme recognition, and MCP.
oci WTFPL ★ 7 -
macOS-only iMessage MCP server for Claude Code. Direct chat.db read, voice-note transcription, FTS5 search, AppleScript send with draft+confirm. Vault auto-export.
mcpb MIT ★ 2 -
Local, private, on-device voice dictation. Hold a key, talk, and the transcript lands at your cursor. Free, offline, and signed + notarized by Apple, so it just opens. Parakeet TDT ASR + optional Qwen3 cleanup. macOS and Windows verified on real hardware. Also a CLI and an MCP voice-input tool for Claude Code.
MIT ★ 7 -
Give your AI agent ears, a voice, eyes, and a studio. MCP server for Gemini image, video, speech, transcription, and music.
-
Companion MCP server for VoxAI — gives your AI ears (live meeting transcripts) and a voice (speech on your Mac). Runs locally.
NOASSERTION -
avagithub.com/iksnerd/avaactive
On-device voice for macOS: dictation, text-to-speech, live call transcription, and an MCP server. whisper.cpp in, Kokoro out — nothing leaves the machine.
MIT -
Voice dictation and meeting notes for Linux: local Parakeet speech-to-text, Claude cleanup, speaker-named transcripts with no bot in your calls, ask your meetings via CLI or MCP.
MIT ★ 1 -
@iflow-mcp/electricessence-telegram-bridge-mcpgithub.com/electricessence/telegram-bridge-mcpupdated this year
Telegram Bridge MCP — An MCP server that bridges AI assistants to a Telegram bot for two-way messaging, confirmations, status updates, and voice transcription.
npm AGPL-3.0-only -
Claude Code WhatsApp channel plugin — run AI directly from WhatsApp, voice transcription, remote tool approval, access control. No API keys, no Docker, just a linked device.
Apache-2.0 ★ 121 -
A phone call MCP server for puch.ai enables users to trigger AI-driven phone calls to customers right from WhatsApp. Instantly place calls, get live transcriptions, summaries, and automate reminders or support all within chat. This bridges messaging and voice for smarter, seamless customer engagement.
-
xalen-mcpgithub.com/vedika-io/xalenupdated this year
MCP server for the XALEN API — full faith-tech marketplace with chat completions, embeddings, image generation, audio transcription, Vedic astrology (kundali, matching, panchang, dasha, yogas, transits, horoscope), Vastu analysis, voice TTS, and billing.
npm MIT -
Read-only, near-realtime reader for local WeChat 4.x chat history on macOS — decrypts the WeChat SQLite databases and exposes messages, images, video, and voice (with transcripts) over MCP and a web UI.
★ 1 -
Native Model Context Protocol (MCP) server exposing HubX's mobile-first multimodal toolchain: vision diagnostics, voice transcription, photo-realistic generation, and spatial design.
MIT -
tapegithub.com/glazec/tapeactive
Self-hostable meeting memory: a meeting bot, a bot-free Mac recorder, and voice recorder uploads in one app. Multilingual transcripts, AI follow-ups, MCP for your own AI. Fair source.
NOASSERTION ★ 1 -
Podcast MCP server and AI podcast generator for Claude, Cursor and Codex: text to podcast with two cloned host voices, episode MP3, SRT transcript, chapters and RSS feed.
oci MIT