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.
-
piper-mcp-servergithub.com/nizovtsevnv/piper-mcp-serverupdated this year
Text-to-speech MCP server using Piper ONNX models
cargo MIT -
@piper-partner/mcpactive
Piper Agent Kit — autonomous MCP (onboard, monitor, trade vault, share cards, cloud chatbot playbook).
npm MIT -
A bare bones voice mcp server using piper
★ 1 -
Agentic smart-speaker manager and voice router: wake word + Whisper + Piper speakers for Linux/macOS, Claude Code/Hermes in tmux over SSH, SIP/WhatsApp/camera calls, MCP server
MIT ★ 1 -
Hands-free voice conversations with Claude Code on Arch Linux: one small MCP server using hyprwhspr's GPU Whisper and a Piper GLaDOS voice, with remote-machine support
GPL-3.0 -
Give any text brain (LLM, agent, MCP host, or CLI) a voice and ears in a Discord voice channel. Whisper STT in, Piper TTS out, under Discord's mandatory DAVE E2EE.
MIT -
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.
-
Chinese TTS aggregation MCP server: Edge-TTS/Piper + engine-level timestamp subtitles
MIT -
live-translate-mcpgithub.com/waxberry-dev/live-translate-mcpupdated this year
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
npm MIT ★ 3 -
Sovereign, local-first voice DevOps assistant (assistant vocal souverain): Ollama LLM, Whisper STT, Piper TTS and MCP tools for KVM, backups and smart home
pypi NOASSERTION ★ 1 -
Local media studio an AI agent can direct: drives ComfyUI, ffmpeg and Piper TTS to make consistent characters, photocards, album art and beat-cut music videos, by hand or over MCP, and records every asset's recipe. A plugin for the Faustus workspace.
MIT -
MCP comedy sidekick — gives LLMs a sense of humor via Ollama-powered comedic personality
npm MIT -
mcp-mia-narrativeupdated this year
MCP server for narrative audio generation - enabling LLMs to create immersive audio experiences
npm MIT -
Self-hosted TTS and programmable announcements for UniFi Protect Smart Chimes, with Home Assistant, REST, MQTT, and MCP.
MIT ★ 2 -
agentvibesgithub.com/paulpreibisch/agentvibesupdated this year
Now your AI Agents can finally talk back! Professional TTS voice for Claude Code, Claude Desktop (via MCP), and Clawdbot with multi-provider support.
npm Apache-2.0 -
🎙️ Fully-local voice for a whole crew of Claude Code sessions on Windows — multi-session, multi-language, multi-voice, one-command install.
MIT -
A text-to-speech tool for AI agents. The agent writes an answer; this tool reads a short summary aloud while the full answer stays on screen. Works online with natural voices or fully offline. Terminal and MCP support. One-command install, no microphone or API key. Linux and WSL.
MIT