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.
-
kokoro-voice-mcp-servergithub.com/noersy/kokoro-voice-mcp-serverupdated this year
—
-
Kokoro Text to Speech (TTS) MCP Server
Apache-2.0 ★ 83 -
Production-ready Kokoro Text-to-Speech MCP Server with Docker Hub deployment
★ 1 -
kokoro-tts-mcpgithub.com/giannisanni/kokoro-tts-mcpupdated this year
MCP server for Kokoro text-to-speech, with adjustable voices/speed and an optional OpenAI-compatible (kokoro-fastapi) backend.
MIT ★ 10 -
Local Kokoro-82M text-to-speech MCP server that speaks through your machine's audio
pypi NOASSERTION -
@sylweriusz/mcp-kokoro-voicegithub.com/sylweriusz/mcp-nexus-voiceupdated this year
MCP Kokoro Voice - Local-first voice synthesis with Kokoro TTS and macOS fallback for AI agents.
npm MIT -
kokoro-ttsgithub.com/neosun100/kokoro-ttsupdated this year
🎙️ All-in-One Docker image for Kokoro-82M TTS - Web UI, REST API, WebSocket, Streaming, Batch, MCP
Apache-2.0 ★ 21 -
A MCP Server built on Gradio that returns English Text as Sound (TTS)
Apache-2.0 -
Cross-platform local text-to-speech MCP server (Windows, macOS, Linux). Powered by Kokoro-82M. Free, offline, no API keys.
Apache-2.0 -
kokoro-mcp-servergithub.com/aparsoft/kokoro-mcp-serverupdated this year
TTS toolkit built on Kokoro-82M with librosa audio enhancement, MCP server for Claude/Cursor, CLI & Python API. Free & open-source for YouTube creators.
Apache-2.0 ★ 15 -
kokoro-tts-mcpgithub.com/scottschram/kokoro-tts-mcpupdated this year
MCP server for Mac Kokoro-82M text-to-speech on Apple Silicon via MLX. Gives Claude Code, Chat, Cowork and Codex a voice. ChatGPT via a workaround. Speaks command line and clipboard. MCP Lazy-loads model (~600MB) for fast subsequent requests.
MIT ★ 4 -
Model Context Protocol (MCP) server for Kokoro text-to-speech with female voice. 100% local, no Python required. Supports SSE and stdio transports.
npm MIT -
kokoro-tts-kotlingithub.com/alexsobolev/kokoro-tts-kotlinupdated this year
Production ready text to speech service built with Kotlin, Kokoro (82M parameters), ONNX Runtime, and Clean Architecture. REST API + MCP server for AI assistants. Multi speaker dialogue, POS aware phonemization, AWS deployment (EC2/Lambda).
Apache-2.0 ★ 10 -
🎤 Make Your AI Agents Speak! Transform text into natural speech using FREE Hugging Face Kokoro TTS model wrapped in a powerful MCP server. Perfect for AI assistants to announce task completions and provide audio feedback.
-
MCP Server wrapper for TTS engines (Kokoro TTS and OpenAI TTS)
NOASSERTION ★ 7 -
digestrgithub.com/aronreisx/digestrupdated this year
An AI-powered daily digest creator that transforms YouTube videos into high-fidelity audio news programs using Gemini summarization and pluggable TTS backends (Gemini & Kokoro). supports CLI, FastAPI, and MCP.
-
tts-apigithub.com/subconscious-labs/tts-apiupdated this year
Kokoro ONNX based TTS API/MCP
MIT ★ 2 -
soliloquy-ttsactive
A text-to-speech MCP server powered by Kokoro — gives Claude Code a voice
pypi MIT -
claude-tts-mcpupdated this year
Local text-to-speech MCP server for Claude Code using Kokoro. Free, offline, no API keys.
npm Apache-2.0 -
Narrated slide walkthroughs for coding agents, voiced on your machine with Kokoro. The link plays in about a second.
MIT ★ 4 -
Dê voz ao seu agente: TTS local e offline sobre MCP (Kokoro-82M, na GPU AMD/NVIDIA ou CPU)
MIT ★ 1 -
Make your terminal talk to you: local text-to-speech (TTS) for Claude Code, Codex and OpenCode on macOS. Your AI coding agent speaks updates out loud with a free Kokoro voice; one voice for many agent tabs, menu-bar app with replay and per-tab mute. MCP server + Claude Code plugin.
MIT -
Local voice runtime and MCP server for coding agents on macOS: one mic, many agents, queued turns, local Whisper + Kokoro.
MIT -
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 -
Local STT/TTS MCP Server — file-based speech-to-text and text-to-speech tools for Claude Code, powered by Whisper.cpp and Kokoro. Self-hosted, zero API cost, ARM Linux compatible.
MIT -
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 -
MCP server for ReadAloud's realtime streaming text-to-speech API (Kokoro-82M) as a single synthesize_speech tool. Free API key, 10,000 free characters, sub-second warm latency. Returns playable WAV audio.
npm MIT -
Fast, standard video generation for AI agents: JSON script in, narrated MP4 out. Local voice (Kokoro TTS), auto captions, TikTok/Shorts, GIFs, screen recording. CPU-only, no browser, no API key.
oci MIT -
Agent-Speakergithub.com/NetDevAutomate/Agent-Speakerupdated this year
A small mcp/tool for agents (Kiro CLI, Claude Code and others...) to speak responses using a wrapper for kokoro-onnx (https://github.com/thewh1teagle/kokoro-onnx) — an 82M parameter ONNX TTS model
★ 6 -
avagithub.com/harshav167/avaupdated this year
Voice interaction MCP server for AI coding assistants - ElevenLabs, Whisper, Kokoro
MIT -
GLaDOS MCP Server - Glados and kokoro TTS feedback inside of your favorite MCP platform
★ 11 -
Local AI voice for coding assistants — TTS & STT via MCP. Kokoro ONNX + faster-whisper, fully offline.
npm Apache-2.0 ★ 11 -
speech-mcp-serverstale
MCP server for text-to-speech conversion using Kokoro TTS
npm MIT -
@mseep/speech-mcp-serverstale
MCP server for text-to-speech conversion using Kokoro TTS
npm MIT -
Create audiobooks locally with Kokoro voices. MCP server for Claude Code and Claude Desktop: say 'create a python course audiobook'.
pypi MIT -
A Claude Code MCP plugin and relay server for remote voice interaction with multiple Claude Code sessions using whisper and kokoro
-
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 -
High-quality TTS with Kokoro-82M model and Claude MCP integration. Voice mode, GPU acceleration, 67 voices, 100-300ms latency.
MIT -
🔌 Exposes Voice & Audio. TTS, voice cloning, audio generation, transcription. Integrates with Kokoro TTS and Whisper STT. (MEOK AI Labs)
pypi NOASSERTION ★ 1 -
MCP server exposing NaN API media tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank
npm MIT ★ 12 -
A desktop phone for your coding agent - it calls you over MCP and you have a natural, spoken back-and-forth. Voice runs fully on-device by default (sherpa-onnx: Parakeet STT + Kokoro TTS), with optional ElevenLabs. Built with Tauri v2 (Rust) + React.
MIT ★ 1 -
Natural voice conversations with Claude Code
pypi MIT ★ 1,461 -
voice-notifier-mcpgithub.com/ominiverdi/voice-notifier-mcpupdated this year
A local MCP notification server with neural voice, desktop, and terminal channels.
MIT ★ 1 -
muse-ttsgithub.com/falcoschaefer99-eng/muse-ttsupdated this year
Three TTS engines, 54 voices, voice cloning. Mac, Windows, Linux. Nothing phones home.
pypi Apache-2.0 ★ 1 -
Self-hosted Docker speech API for OpenAI-compatible transcription and text-to-speech, streaming ASR, voice cloning, phoneme recognition, and MCP.
oci WTFPL ★ 7 -
Give Claude your Telegram (MCP connector) and phone an AI assistant on Telegram calls, in Persian or English, with an optional Jarvis voice. Self-hosted.
MIT ★ 1 -
A collection of Model Context Protocol (MCP) servers enabling AI assistants to securely access and interact with local files, Gmail, and web content, facilitating integration with MCP-compatible applications.
MIT ★ 1 -
Give your AI coding agent a voice: it speaks its decisions and questions, you answer by talking, and it can change your desktop. Local by default.
MIT ★ 19 -
Local-first video and podcast factory. One JSON storyboard in, finished MP4 out. No cloud render, no per-video fees. Works with any MCP agent.
MIT -
Local, on-device voice notifications for coding agents (Claude Code, Codex CLI) — MCP tool, CLI, and lifecycle hooks backed by a local TTS bridge.
MIT ★ 2 -
Production zero-shot voice cloning & studio TTS server in Rust. 646+ languages, cross-lingual synthesis, voice blending, biometric verification, broadcast DSP mastering, MCP protocol & embedded React 19 UI. Fast, private, fully self-hosted.
NOASSERTION ★ 3 -
Electronic butler for LLM-assisted work. An OpenCode plugin that speaks your agents' messages through a local TTS daemon, parks the colliding ones onto a notification card with a Listen button, and never lets two voices overlap. Ships voice MCP + persona + cards in one package.
MIT -
The arcade: games made from what MCP servers said on the wire. Ghost on the Menu (a replay shooter) and Vibe Typer (a typing game where you are the coding agent), both playable on a phone, from npx, or as MCP servers. Cabinets read mcp-arcade tapes and never touch the score.
npm MIT -
Open-source AI faceless video generator for TikTok, YouTube Shorts and Reels on Apple silicon Macs. A free, local alternative to Higgsfield Content Factory: a script becomes a 30–120 s vertical video from about 8 AI images a minute, with voiceover, word-by-word subtitles and music. No watermark. MCP server for Claude.
MIT ★ 6