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.
-
Generate long-form multi-speaker audio from YAML using Google Cloud high quality TTS models (incl. EU ML Processing!). Python library with CLI, FastMCP, and ADK adapters; async jobs so agents don’t block on synthesis.
Apache-2.0 -
musmcpgithub.com/erno-szabados/musmcpupdated this year
MCP Server for csound-powered audio sample synthesis
MIT ★ 3 -
🔌 Lets an MCP client analyze images, videos, and audio for deepfake manipulation artifacts. Checks metadata, provenance chains, and synthesis indicators.
pypi MIT -
A Model Context Protocol server for generating authentic 8-bit music. Integrate chiptune composition tools into AI assistants like Claude, Cursor, and VS Code. Create retro melodies, rhythms, and chord progressions with real-time audio synthesis.
npm ★ 3 -
wordcast-mcpgithub.com/rocnubie/wordcast-mcpupdated this year
WordCast is a browser-based text-to-speech reader that converts written content into audio entirely on your device. There is no backend server involved: text, files, and URLs are processed locally using the speech synthesis voices already installed on your operating system.
MIT -
Tavus MCP Serverno update data
Enable AI video generation, replica management, conversational AI, lipsync, and speech synthesis through a comprehensive MCP server for the Tavus API. Manage AI replicas, generate videos, create interactive conversations, synchronize audio, and generate speech seamlessly within MCP-compatible applications. Access full Tavus API v2 capabilities with robust error handling and easy integration.
smithery -
@ray0404/zig-audio-mcpgithub.com/ray0404/zig-audio-mcpupdated this year
MCP server for Zig audio/DSP programming assistance - run with: npx @ray0404/zig-audio-mcp
npm MIT -
MCP server for game audio generation — BGM, SE, jingles as 16-bit WAV. Zero dependencies, pure Zig.
MIT ★ 1 -
Deterministic vocal instrument engine — additive synthesis with formant control, real-time WebSocket streaming, MCP server, and cockpit UI
npm MIT -
A powerful Model Context Protocol (MCP) server that provides text-to-speech and audio playback capabilities for Claude Desktop and other MCP clients.
MIT ★ 2 -
cochlea-mcpgithub.com/richer-richard/cochleaupdated this year
MCP stdio server for cochlea: agents render, probe, diff, and verify audio as tools
cargo MIT OR Apache-2.0 -
higgs-audio-webgithub.com/neosun100/higgs-audio-webupdated this year
🎵 All-in-One Docker deployment for Higgs Audio v2 with Web UI, REST API & MCP support. Features: Expressive TTS, Zero-Shot Voice Cloning, Multi-Speaker Dialog, Text Profile Voice.
Apache-2.0 ★ 3 -
MCP server and CLI for AI agents to control SuperCollider (sclang)
ISC -
@daanrongen/sclang-mcpgithub.com/daanrongen/sclang-mcpupdated this year
MCP server for SuperCollider — evaluate sclang code, boot scsynth, and inspect server state
npm MIT -
MCP server generating coherent 16 kHz mixed audio scenes from text - speech, music, sound effects and ambience in one pass - powered by MiDashengLM-Gen (Xiaomi Research). Local-first, runs entirely on your CUDA GPU. Apache-2.0.
Apache-2.0 ★ 2 -
A DAW with its own audio engine and an MCP bridge, so an AI agent can compose, mix, listen and export music. FFmpeg is used only to decode and encode.
MIT -
Sovereign local-first AI voice studio. Neural speech synthesis, zero-shot voice cloning, zero-latency dictation, and MCP agent voice I/O. Built with Tauri & FastAPI.
AGPL-3.0 -
muse-tts-embedgithub.com/falcoschaefer99-eng/muse-tts-embedupdated this year
Persistent audio player embedded in Claude's chat. 54 voices, voice cloning, play/pause/seek/download. Fully local.
NOASSERTION ★ 3 -
Sound creation for AI coding agents. Local synthesis, layered DSP, CLI and MCP.
Apache-2.0 -
The Infinite audiovisual engine as an MCP server for Claude Desktop, Cursor and Windsurf. Free and open source.
npm MIT -
puredata-mcp-servergithub.com/j0kz/mcp_pure_dataupdated this year
MCP Server for Pure Data & VCV Rack — parse, generate, analyze, and control Pd patches and VCV Rack modules with AI
npm MIT -
Four-channel chiptune tracker toolkit for Codex, Claude, Hermes and other agents. JSON/Python composition, real MOD exports, desktop editor and HTML players.
MIT ★ 1 -
@theproductivepixel/aittsmactive
MCP stdio server for AI TTS Microservice — connects AI agents, IDEs, and MCP-compatible clients to the unified TTS API via tool calls
npm MIT -
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 -
salban-mcp-servergithub.com/WizardofTryout/salban-mcp-serverupdated this year
Hardened Model Context Protocol (MCP) server for the SAL BAN Monolith Engine. Enables agentic AI assistants (Claude, Cursor) to program sequences, load audio samples, and control the synthesizer in real-time, live. Live Sessions with parameter control and human interaction
NOASSERTION -
veadioactive
Veadio MCP Server — AI voice synthesis and document management for coding assistants and automation
npm MIT -
MCP server providing authentic 16-bit SNES gaming sounds, R2D2 expressive emotions, and professional music synthesis for AI agents
cargo MIT -
Claude Code plugin + MCP server for Woodstitch: blinded human listening tests on text-to-speech audio
MIT -
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 -
MCP server for the Woodstitch API: paid human listeners judge your text-to-speech audio blind (pairwise preference or human-vs-AI detection). Not MOS.
pypi MIT -
synthlab-mcp-servergithub.com/j0KZ/synthlab-mcp-serverupdated this year
AI-powered synthesis lab — Compose songs, generate Pure Data & VCV Rack patches, map MIDI controllers, and control live synths through Claude
npm MIT ★ 5