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.
-
mcp-asractive
npx launcher for the mcp-asr Python MCP server
npm MIT -
autoglm-asr-mcpgithub.com/Starrylyn/autoglm-asr-mcpupdated this year
MCP server for audio transcription using AutoGLM ASR API
npm ★ 6 -
simple-asr-mcpgithub.com/selentar/simple-asr-mcpupdated this year
Minimal MCP server for local speech recognition using faster-whisper
pypi MIT -
glm-asrgithub.com/neosun100/glm-asrupdated this year
All-in-One Speech Recognition Service based on GLM-ASR-Nano | Web UI • REST API • MCP Server • Long Audio Support
pypi Apache-2.0 ★ 7 -
audio-asr-mcpactive
将本地音频转为文本或 SRT 的 Whisper MCP 服务,支持文件输出和纯文本回退。
npm MIT -
@bachstudio/mcp-asr-diarizeactive
MCP server for speaker-attributed speech-to-text: tells apart who is speaking (voiceprint / diarization) and transcribes what they said. Point it at any backend with --url.
npm MIT -
cloud-asr-mcpgithub.com/danielrosehill/cloud-asr-mcpupdated this year
MCP server using audio multimodal models for transcription and output styling in one pass. Format-specific outputs (email, todo, blog, etc.) via OpenRouter, Voxtral, OpenAI, and Gemini.
npm MIT -
B 站视频转笔记工具集:批量字幕下载 / 必剪 ASR 转写 / MCP 工具面
pypi MIT -
tonyq-mimo-mcp-serverupdated this year
MCP Server for MiMo multimodal capabilities (image, audio, video understanding, ASR, TTS)
npm MIT -
B站综合查询 MCP Server:视频元数据、字幕/ASR 转录、弹幕、评论、UP主信息一站式查询
pypi MIT -
System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.
Apache-2.0 ★ 262 -
音视频到转写文稿与结构化纪要的一条命令工具链:拆轨、人声分离、说话人分离、多引擎识别、字幕与 RTTM、规范 docx。默认离线,可选云端 ASR,支持续跑与批量,附 MCP 服务、跨会议检索与泳道图。 | One-command AV to transcript and minutes: demux, separation, diarization, multi-engine ASR, SRT/VTT/RTTM, docx. Offline-first, optional cloud ASR, resumable batches, MCP server and cross-meeting search.
MIT -
Offline voice control for OpenCode: push-to-talk ASR (SenseVoice + sherpa-onnx) with MCP tools
MIT -
飞鸽外呼本地平台(FOP):REST/CLI/MCP/SKILL + 本地 ASR + DeepSeek 后处理 + 呼出编排(MIT)
MIT -
ListenMiao: local web app for MediaTek Research's Breeze ASR 25/26. Turn Taiwanese Mandarin, Mandarin–English code-switching and Taiwanese Hokkien into subtitles and transcripts without uploading audio. Hotwords, speaker diarization, subtitle editor, SRT/DOCX export, burn-in, CLI, MCP server, Agent Skill; CPU, Intel GPU or NVIDIA/AMD GPU.
MIT ★ 2 -
Review-first Chinese teaching video editing for Final Cut Pro: local ASR, auditable cuts, synchronized captions, and FCPXML handoff.
MIT ★ 1 -
Automated video localization, multi-engine ASR, subtitle translation, and dual-version FFmpeg hardsub pipeline for AI agents, CLI, and MCP hosts.
pypi MIT -
douyin-transcript-mcpgithub.com/mei-shui-xing/douyin-transcript-mcpupdated this year
Local-first, read-only Douyin speech transcription MCP using Qwen3-ASR and OpenAI Secure MCP Tunnel; no VPS required.
MIT -
dsh-qwen-mm-pluginsgithub.com/ShuiHan268/dsh-qwen-mm-pluginsupdated this year
DeepSeek Harness 的 Qwen-MM-Plugins 集成插件:12 个多模态 MCP 工具(视觉/OCR/定位/ASR/音视频)、Web 设置页(粘贴 Qwen API Key 即用)、内置技能与一键安装器
Apache-2.0 ★ 4 -
Self-hosted Docker speech API for OpenAI-compatible transcription and text-to-speech, streaming ASR, voice cloning, phoneme recognition, and MCP.
oci WTFPL ★ 7 -
免密码抖音/本地视频语音转写与无水印下载服务:4 级降级下载链 + SenseVoice 离线 ASR + MCP Server + Web 校对台 | Self-hosted Douyin & short-video speech-to-text, downloader & MCP server
MIT -
Valargithub.com/jvogan/Valarupdated this year
Give your AI agent a voice. Local speech stack for Apple Silicon: TTS, ASR, forced alignment, voices, daemon, and MCP bridge.
MIT ★ 1 -
Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用
pypi MIT ★ 3 -
Local offline speech recognition for Russian speech with German words: ASR model ensemble with word-level voting, diarization, desktop app, CLI and MCP server. Research notes included.
GPL-3.0 -
vidscribegithub.com/XFWang522/vidscribeupdated this year
🎬 MCP Server + Agent Skill + CLI — Transcribe any video URL to text. Plug into Claude Desktop / Cursor / Windsurf / Codex. Supports Bilibili, YouTube, TikTok, 1000+ sites × 5 ASR providers.
MIT ★ 4 -
Dou-wiki — Local Douyin knowledge base for AI agents. Turn Douyin videos & image notes into searchable, source-linked Obsidian Markdown via MCP — local download, Qwen3-ASR transcription and OCR on macOS; your agent's own model does correction & analysis. 面向 AI Agent 的本地抖音知识库。
MIT ★ 1 -
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth, passkeys, anti-bot reach, on-by-default prompt-injection defense, plus on-device multimodal ASR/OCR. A single Rust binary — not a browser.
cargo MIT ★ 18 -
MCP server for M5Stack Petit — camera, display, sensors, TTS/ASR, rover, printer / M5Stack Petit用MCPサーバー(カメラ・ディスプレイ・センサー・TTS/ASR・ローバー・プリンター)
Apache-2.0 -
Local, private, on-device voice dictation. Hold a key, talk, and the transcript lands at your cursor. Free, offline, and signed + notarized by Apple, so it just opens. Parakeet TDT ASR + optional Qwen3 cleanup. macOS and Windows verified on real hardware. Also a CLI and an MCP voice-input tool for Claude Code.
MIT ★ 7 -
bilibili-mcp-servergithub.com/zmq175/bilibili-mcp-serverupdated this year
B站 MCP Server:查询直播状态、粉丝牌、历史弹幕,支持直播内容 ASR+视觉分析
★ 1 -
Local CrispASR transcription for Codex and MCP agents. English via Cohere, Chinese via Qwen3-ASR 1.7B.
pypi MIT ★ 1 -
MCP operator stack for coding agents with 3D face UI, tmux bridge, multi-agent helpers, mobile remote access, ASR, and realtime voice feedback.
MIT ★ 1 -
yandex-mcp-serversgithub.com/minakovai/yandex-mcp-serversupdated this year
Yandex API MCP Servers - GPT, Vision OCR, SpeechKit TTS/ASR, Search
MIT -
LLM-based HFACS classification of ASRS aviation incident reports. Includes experimental data processing, classification models, evaluation methods, and MCP server for data access.
NOASSERTION ★ 2 -
Windows-friendly maintained fork of douyin-mcp-server with browser fallback and SiliconFlow cloud ASR.
Apache-2.0 -
动态视听 · Windows MCP for adaptive video frames, audio, subtitles and optional ASR. Shared runtime and generic Agent Skill.
NOASSERTION -
openclaw-knowledge-distillergithub.com/destinyfrancis/openclaw-knowledge-distillerupdated this year
Open CLAW Knowledge Distiller · 龍蝦知識蒸餾器 — Turn YouTube/Bilibili videos into structured knowledge articles. Local Qwen3-ASR MLX + AI summarization. MCP server for Claude Code / Open CLAW agents.
★ 65 -
Charlie 语音助手 — 本地部署的私人AI助理,零配置Demo模式开箱即用,支持语音交互、ESP32开发板终端、飞书推送、MCP技能扩展。ASR→大脑→TTS语音闭环,Demo规则模式无需任何API key即可对话。
-
[ALPHA] Local-first voice studio - wake-word, ASR, command bus. Implements the Storytold craft-app harness - see storytold/artcraft.
Apache-2.0 -
garbleworksgithub.com/SamsonCyber/garbleworksupdated this year
Authorized LLM red-team harness: recipes, scoped fire, evolutionary search, Wilson ASR. MCP + API + TUI.
Apache-2.0 -
lanterngithub.com/xingshizhai/lanternupdated this year
Local LAN service discovery for AI services (LLM/ASR/TTS) via mDNS + a cross-subnet registry (LSRP), exposed to agents through MCP and a CLI/Go SDK.
GPL-3.0 -
The Advanced Scientific Research (ASR) Graph of Thoughts (GoT) MCP server is a highly efficient implementation of the Model Context Protocol (MCP) that allows for sophisticated reasoning workflows using graph-based representations.
pypi Apache-2.0 ★ 12 -
Self-verifying TTS: generate, transcribe with an independent ASR, measure, escalate and keep best. CLI + REST + MCP server for agents.
MIT ★ 1 -
Enterprise AI Meeting Agent: Contextual ASR speech repair, multi-turn Chain-of-Thought commitment disambiguation, and gated MCP tool execution.
MIT -
Free, agent-controllable web app for creating and editing motion graphics, with a built-in template library, MCP integration, local ASR, and practical video editing tools.
MIT ★ 3 -
Codex-native-long-video-memorygithub.com/NitcanKen/Codex-native-long-video-memoryupdated this year
Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
Apache-2.0 ★ 4 -
musicodecupdated this year
MCP server that gives text-only LLMs a perception channel for music: arrangement facts (sections, stems, facture textures, energy) + timestamped ASR lyrics + upstream confidence, extracted from audio. Perception, not conclusions.
npm MIT -
dsh-qwen-mmgithub.com/RRRosmontis/dsh-qwen-mmupdated this year
Qwen-MM-Plugins integration bundle for DeepSeek Harness (dsh) — multimodal MCP tools (vision, OCR, ASR, search, video, Blender, FreeCAD) + image attachment bridge. 让 DeepSeek Harness 原生支持多模态。
MIT ★ 1 -
Local meeting transcription MCP server: Whisper large-v3 + Qwen3-ASR on your own GPU, speaker labels, verify flags, optional Korean minutes. Audio never leaves your machine.
Apache-2.0 -
Local dictation and meeting notes with Whisper or the OpenAI API. Custom Whisper models, MCP history access, and shared engines over LAN/Tailscale. Optional Parakeet/Nemotron (Windows x64, Linux x86_64), Qwen3-ASR/Moonshine (Windows x64), and Parakeet CPU/experimental MLX (Apple Silicon).
MIT ★ 269 -
yojana-sahayak-assistantgithub.com/Subh24ai/yojana-sahayak-assistantupdated this year
Fully offline, multilingual voice AI agent that helps Indian citizens discover government welfare schemes in Hindi & English. Uses Whisper ASR, fine-tuned Qwen2.5 (QLoRA), FAISS RAG, and an MCP tool server — all designed for air-gapped deployment. Covers 2,872 schemes from myscheme.gov.in.
★ 1 -
roshan-harf-mcpgithub.com/dwin-gharibi/roshan-harf-mcpupdated this year
Self-hostable MCP server wrapping Roshan AI Harf's HTTP and WebSocket APIs, enabling Persian speech-to-text, alignment, real-time streaming, and speaker analytics for Claude and other MCP-compatible applications.
NOASSERTION -
douyin-summary-mcpupdated this year
MCP服务:从抖音分享链接提取音频、进行语音识别并整理对话内容
npm MIT -
douyin-summary-mcpgithub.com/yourusername/douyin-summary-mcpupdated this year
MCP服务:从抖音分享链接提取音频、进行语音识别并整理对话内容
pypi MIT -
mcp-speech-recognitionupdated this year
语音识别MCP服务 - 基于豆包语音识别API的音频文件转文字工具
npm ISC -
mocovoice-mcp-servergithub.com/mocomoco-inc/mocovoice-mcp-serverupdated this year
mocoVoice MCP Server
MIT ★ 3 -
b2a777github.com/e8b298/b2aupdated this year
B2A (Bilibili to Agents) — 让 AI Agent 能观看和倾听B站视频的多模态 MCP 插件
pypi MIT -
MCP server for downloading and extracting content from Bilibili videos
pypi MIT -
Natural voice conversations with Claude Code
pypi MIT ★ 1,459 -
Local multimodal inference service
MIT ★ 5