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.
-
Offline voice control for OpenCode: push-to-talk ASR (SenseVoice + sherpa-onnx) with MCP tools
MIT -
Audit, monitor, repair and voice-control Grandstream UCM phone systems from any AI agent, CLI or voice. MCP server + Agent Skill. Tested on UCM6304 fw 1.0.33.30.
MIT -
Control Spotify from local Codex tasks on Windows. Play songs and playlists, queue tracks, skip songs and adjust volume without switching windows. Supports typed requests and voice where available.
NOASSERTION -
Voice-controlled MCP hardware gateway for UNIHIKER K10: reusable skills, composition, and Codex-generated programs.
★ 2 -
voice-mcp-servergithub.com/dskill/voice-mcp-serverupdated this year
Remote MCP server for voice control via Claude Mobile - this repo was committed using itself! 🎤
★ 1 -
voice-agi-mcpgithub.com/marc-shade/voice-agi-mcpupdated this year
Stateful voice-controlled AGI system combining local STT/TTS with conversation management
-
Voice control for edge devices: on-device agent (listen → LLM tool-calling → device action → speak). Swappable cloud/local backends. By embedai.com.cn
MIT -
@anomalypoint/voice-boxgithub.com/anomalypoint/voice-boxupdated this year
Local voice control panel for AI agents. Give each agent its own voice, queue and manage what they say, with OpenAI or ElevenLabs TTS.
npm MIT -
Google Voice from the command line and as an MCP server for AI agents. Read and send texts from your own number, through a send door you control.
MIT -
MCP server for Vicsia Studio — control your voice agents from Claude
pypi MIT -
Hands-free voice assistant that lets Claude control your Android phone (MCP + AccessibilityService)
MIT -
Text-to-speech MCP server for AI agents, with multiple speech engines, emotion control, and voice customization.
MIT ★ 1 -
Windows desktop RVC voice conversion for Dot, with an easy installer and optional local MCP controls. Bring your own model.
MIT -
Verifiable multi-agent voice-operations control plane with safety gates, MCP tools, a 2,048-case adversarial evaluation, and CI.
-
A voice assistant that turns your voice notes into real tasks and actions, while keeping you in control of important decisions.
MIT ★ 1 -
Windows voice for Claude and Codex. Reads replies aloud with Inworld or ElevenLabs, independent voice profiles, a shared queue, and a GUI control panel.
MIT ★ 1 -
SparkHome: a tvOS-style home screen and voice assistant for the NVIDIA DGX Spark. Plugins for controllers, tiles and connectors; MCP for agents. MIT.
MIT ★ 39 -
WhatsApp channel plugin for Claude Code — connect your WhatsApp to an AI agent. QR scan, voice transcription, access control, media support.
MIT ★ 18 -
A voice-controlled care necklace for seniors living alone. ESP32-S3 firmware, Python MCP tools and a Next.js caregiver dashboard for check-ins and activity approvals. Top 5 Finalist, Dell InnovateDash 2026.
NOASSERTION -
MrJ-JMRI-MCPgithub.com/HO44-PROJECT/MrJ-JMRI-MCPupdated this year
JMRI CLI and MCP server for DCC model railroads — control your layout by voice or chat (Claude, xiaozhi/Kira) or from a terminal (jmri-cli)
go AGPL-3.0 ★ 1 -
gemini-tts-mcpgithub.com/notsointresting/gemini-tts-mcpupdated this year
🎙️ High-fidelity Text-to-Speech (TTS) for Gemini CLI & MCP. Powered by Gemini 2.5 Flash/Pro with 30+ premium voices and natural language style control.
MIT ★ 5 -
c4-mcp-appgithub.com/randybritsch/c4-mcp-appupdated this year
Voice control for Control4 home automation via MCP - PWA + Node.js backend
-
Gamepad controller for Rhino 8 on macOS: orbit, pan, zoom, magnetic geometry selection & haptics. Optional voice-to-VS Code agent via Rhino MCP.
Unlicense -
Local GPU text-to-speech for AI agents via MCP - Chatterbox turbo/nano/multilingual, zero-shot voice cloning, resident worker with sentence batching, and a local web panel for worker control, model state, speak, replay and stop.
MIT ★ 2 -
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 -
reachy-mini-mcpgithub.com/jackccrawford/reachy-mini-mcpupdated this year
Reachy Mini MCP | Give your AI a body. This MCP server lets AI systems control the Pollen Robotics Reachy Mini robot. | Speak, listen, see you, and express emotions through physical movement and voice. | Works with Claude, Windsurf, Cursor, or any MCP-compatible AI. | Zero robotics expertise required.
MIT ★ 30 -
HomeLink → Alexa → XiaoZhi MCP bridge for ESP32 voice control. 日本账号、私有授权、家电开关。
MIT ★ 1 -
akai_mcpgithub.com/skenglord/akai_mcpupdated this year
A cloud hosted analogue drum machine/sampler/sequencer with full voice/text to commands control via an MCP server.
-
personaplexgithub.com/neosun100/personaplexupdated this year
🎙️ Real-time Full-Duplex Conversational AI with Voice and Role Control | All-in-One Docker | Multi-language UI | REST API | MCP Support
MIT ★ 12 -
Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. 面向 AI 智能体的硬件鼠标 MCP:USB HID 控制与语音听写,需要兼容的 uMouse 设备与固件。
mcpb MIT ★ 404 -
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 -
Independent ESP32-S3 voice-AI robotics platform derived from XiaoZhi AI Chatbot (MIT) — Yana Wheelbot board, chassis, and web controller.
MIT ★ 1 -
voiceos-todoistgithub.com/gabeperez/voiceos-todoistupdated this year
Voice-control Todoist from VoiceOS — local MCP server + one-way Apple Reminders sync. One-command installer.
MIT -
c3github.com/andrometiq/c3active
One Telegram bot as a remote control for the Claude Code and Codex sessions already running on your machine — a topic per project, voice notes transcribed, permission prompts as tappable buttons, and a durable queue when nothing is attached. Self-hosted Go broker + MCP adapters.
MIT ★ 2 -
Cross-platform Swift-based MCP server providing comprehensive text processing, content analysis, and Apple ecosystem integration. Features 21 professional tools including PII redaction, summarization, intent analysis, Shortcuts execution, and Voice Control with enterprise-grade security.
MIT ★ 4 -
grumble-mcpactive
Use Grumble from your coding agent: read your servers, channels and messages, watch channels, see notifications and control voice, through the Grumble desktop app on your computer (MCP server).
npm MIT -
Windows-only local-first VRM desktop companion with voice-output lip sync, animations, and MCP controls.|Windows 本機 VRM 桌面角色陪伴。
MIT ★ 2 -
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 -
local-llm-speakergithub.com/geoClink/local-llm-speakerupdated this year
Private, offline smart speaker built from scratch. Raspberry Pi 5 brain running Whisper STT, Ollama + Qwen3, and Piper TTS. MCP tools for weather, sports, and BBQ probe. Web dashboard for full control. No cloud. No subscription. No voice data leaving your network.
-
roxels-mcpgithub.com/trebu-org/interviewerupdated this year
MCP server for Roxels. Let AI agents control Roxels directly: set up end-to-end AI voice conversations — webhooks, data sources, app embeds, structured-result extraction — and define each conversation's goals. Use Roxels to onboard new customers to your product or gather insights from users by letting them speak or share their screen.
pypi MIT -
tesseract-voice-aigithub.com/jmanhype/tesseract-voice-aiupdated this year
🎯 Tight end-to-end MCP+GraphQL control plane with real-time test orchestration, dry-run workflows, and interactive confirmation dialogs. Features Strawberry GraphQL, Apollo Router federation, and Next.js interface.
★ 1 -
@iflow-mcp/mcp-voice-hooksgithub.com/johnmatthewtennant/mcp-voice-hooksupdated this year
Real-time voice interaction for Claude Code. Speak naturally while Claude works - interrupt, redirect, or provide continuous feedback without stopping.
npm UNLICENSED -
Enhanced JARVIS MCP with integrated services (Gmail, Slack), intelligent summarization, and human-like delivery
npm MIT -
Preview and dispatch AI phone calls through Vapi, Bland AI, Retell AI, and Telnyx with a TypeScript SDK, CLI, and MCP server.
npm MIT -
MCP server for Vicsia — controle systeme par la voix (apps, paths, settings)
pypi MIT -
Your iPhone farm, on autopilot. Free and open-source — plug in iPhones and Octagon runs them from your Mac. Real taps, no APIs, no cloud.
MIT -
ricochet-mcpgithub.com/igoryanba/ricochetupdated this year
Control your AI coding agents from Telegram. MCP server for Cursor, Claude Code, Windsurf.
npm MIT -
Self-hosted AI phone assistant with Twilio, OpenAI GPT-Live, MCP, live transcripts, keypad navigation, and direct human controls.
MIT ★ 1 -
MCP server for AutoRev AI. Run your field service business from Claude: answer calls, book and dispatch jobs, build estimates, chase invoices. For HVAC, plumbing, electrical, roofing and pest control.
MIT