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.
-
Loudness compliance verdicts against formal published standards (EBU R128, ATSC A/85) — pass/fail with exact deltas and remediation, not raw meter output. CLI + MCP over one ffmpeg-based engine.
pypi MIT ★ 1 -
Audio perception for AI agents: measure, see, compare, edit and synthesize sound over MCP. Loudness, spectrograms, pitch, events, transcription, cleanup.
pypi MIT -
Loudness (EBU R128 / BS.1770-4), true-peak and voice-quality analysis for AI agents. Reads local files as well as URLs.
npm MIT -
MCP server for driving Adobe Premiere Pro from an AI assistant, with tools that verify their own writes, measure colour and loudness, and judge whether an edit is ready to post
MIT ★ 1 -
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.
npm MIT ★ 5,992 -
Talk with Claude out loud on your Mac — on-device speech with whisper.cpp. An MCP server.
npm MIT -
Rehearse your presentation out loud: turn a deck into an Aitho talk from Gemini CLI (remote MCP, OAuth).
MIT -
Sandboxed file-access MCP server for Claude Desktop — loud failures, verified atomic writes, built-in undo, .docx reading
MIT ★ 1 -
Voice-first shared household ledger for Alexa+, as an MCP server. Record expenses out loud, settle up in the fewest payments.
MIT -
A simple MCP plugin that returns the provided thought string. Useful for agentic reasoning, cache memory, or when you want to "think out loud" in a workflow.
Apache-2.0 -
ElevenLabs MCP server for podcast production: multi-speaker dialogue, music, sound effects and episode assembly with loudness normalisation.
MIT -
Practise sales calls out loud against AI clients, graded by a coach agent. Symfony AI + MCP, open models, AGPL-3.0.
AGPL-3.0 ★ 1 -
Voice MCP server: your agent hears you and answers out loud. Russian-first, Yandex SpeechKit, zero dependencies.
MIT -
Echoteka MCP server: AI music mastering, loudness analysis and AI-trace cleanup for Claude, Cursor and other MCP clients
MIT -
An MCP server that puts music under a voice: bckgrnd-msc's Rust/WASM engine, levels set by measured loudness.
npm MIT -
Two read-only MCP servers that let Claude query a telehealth practice's people and content, and say out loud what they could not see.
-
Ask out loud, and Judith answers right on your screen (Throught your own Claude claude ) : drawings, 3D models, spoken answers. on Windows
MIT -
Ask a spreadsheet questions out loud. An MCP server that makes tables navigable by voice for blind and low-vision users.
MIT -
Secure MCP server to control Ableton Live 12 from Claude and other MCP clients: tracks, clips, devices, mixing, loudness analysis. Not affiliated with Ableton.
MIT -
clinicalai-mcpgithub.com/OpenClinicalAI/clinicalai-mcpupdated this year
Open-source MCP servers for clinical decision support — calculators, drugs, evidence, terminologies. Local-first, PHI-aware, fail-loud.
Apache-2.0 ★ 1 -
winnerads-ai-editorupdated this year
AI Editor MCP — prod-grade scenario rendering with cinematic auto-trim, multi-modal scene analyzer, DirectorAI rule-based framing, EBU R128 loudness, GPU encoder auto-detect, and post-render QC.
npm UNLICENSED -
Let Claude listen to your Mac — system audio or mic — as compact text: key, chords, tempo, melody, tuning, loudness, speech. Local, audio-only Claude Code plugin + MCP server.
MIT -
An agent-native browser DAW. WebMCP gives your agent ears: it renders the loop offline and measures loudness, spectrum and masking conflicts the DOM can't show.
MIT -
Exact math execution layer for AI agents: fractions, finance, units, dates. MCP server + DSH plugin, 19 packs, fail-loud errors, 19,000 acceptance tests.
pypi MIT -
A guard MCP server for Alexa+ - checks what any add-on asks for and lets the family say yes or no, out loud, before it touches a lock, a card, or money.
MIT -
Local video tools for AI agents that read text and images but not video: contact sheets, transcripts, cut, loudness and sync checks, served over MCP.
pypi MIT ★ 1 -
Open-source alternative to Adobe Audition for people and AI agents: multitrack audio editor in the browser, MCP, live sessions, spectral repair, loudness mastering.
npm NOASSERTION ★ 4 -
Agent tooling for ClaraConverts — Clara, an AI agent that website visitors talk to, out loud or by text, and that turns them into customers. agents.txt, an install Skill, and MCP servers for tool access.
Apache-2.0 -
Ask out loud what public funding you can actually apply for. Self-hosted MCP server (Streamable HTTP) over live grants.gov data, with honesty gates that refuse to guess. Built for the Amazon Developer Hackathon (Alexa+ track).
MIT ★ 1 -
AI assistant editor for Premiere Pro and DaVinci Resolve. Open-source MCP server for Claude Code and Codex: logs footage, transcribes, builds rough cuts, makes subtitles, checks colour and loudness.
mcpb MIT ★ 2 -
Fix a voiceover mistake without re-recording: re-voice one sentence in your own voice and splice it in with matched loudness, EQ and room tone. Open-source Overdub alternative. CLI + MCP server.
pypi MIT -
Make agent failures loud — deterministic checks that catch LLM agents claiming done when the work is placeholder, unbacked, stale, miscounted, or missing pieces. CLI + MCP server + watch mode + LangChain adapter + second-pass verification against the system of record, zero dependencies.
pypi MIT -
🔞 For human–AI romance — let your AI companion spin tonight's BDSM scene: body parts, bondage, training, props, and a line to say out loud. Zero-dependency MCP server (streamable HTTP) + gothic web UI.
MIT ★ 2 -
scratch-mcpgithub.com/FromArkZoo/scratch-mcpupdated this year
An MCP server that lets an AI agent build and run real Scratch projects — readable text compiled to a runnable .sb3 (full Scratch 3 block palette, fail-loud) and driven in a live Scratch editor.
★ 1 -
Local, offline web studio for game, video, podcast and social assets: images, 3D models, SFX, music and voices from ~100 open-weight models. Shared asset library, single-GPU job queue, prompt improver, commercial-licence filter, loudness-matched export presets and a built-in MCP server.
Apache-2.0 -
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 -
MCP server for editing, processing and measuring audio in Audacity 3.7 through mod-script-pipe
npm MIT ★ 1 -
Short-drama delivery packs: burned subtitles in the safe area, -14 LUFS mastering, clean masters, covers, rights check, acceptance audit, and an MCP server for AI agents.
pypi Apache-2.0 -
Does your AI-generated sound match the prompt? Local QA for generative audio — check, rank, QC, picture-fit and library search with EmbeddingGemma 2. CLI, web workbench, MCP server.
MIT ★ 16 -
Declarative multi-track audio engine for AI agents: YAML timelines to TTS speech, music beds and SFX with sidechain ducking, EBU R128 mastering and subtitles. CLI, MCP server, Agent Skill and Claude Code plugin.
npm Apache-2.0 ★ 2 -
perception-mcpgithub.com/egorthinks/perception-mcpupdated this year
Perception & verification MCP server for AI agents: media_assert (declarative pass/fail QC for generated media), image diff (pixelmatch + SSIM), readable text tiles for small print & handwriting, video tools (frames on demand, scenes, QC defects, pacing dynamics, attention heatmaps, scene diff), and full audio DSP (pitch, BPM, key, LUFS, spectrograms).
pypi MIT License Copyright (c) 2026 Egor Fedorov Pe