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.
-
qwen3-tts-mcpgithub.com/hz1ulqu01gmnZH4/qwen3-tts-mcpupdated this year
—
WTFPL ★ 1 -
—
Apache-2.0 -
Qwen3-Coder MCP server for Claude Code with 64GB RAM optimizations
-
Self-hosted Qwen3 retrieval server with Embedding, Reranker, MCP, and Web console.
★ 7 -
qwen3-tts-mcpgithub.com/Allen-han21/qwen3-tts-mcpupdated this year
MCP server for Qwen3 TTS - Voice synthesis, cloning, and design for Claude Code
-
qwen3_mcpgithub.com/marduk191/qwen3_mcpupdated this year
MCP server for LM Studio with 80+ tools - file ops, git, web search, skills system
npm MIT ★ 14 -
qwen_embedding_06_mcpgithub.com/AuraFriday/qwen_embedding_06_mcpupdated this year
An MCP server for generating Qwen3 embedding vectors
Apache-2.0 ★ 1 -
@hugobiotech/vision-bridgeupdated this year
Local MCP bridge for fixed Qwen3.5-VL-Plus visual image analysis
npm -
统一的本地 TTS 调度服务(Breeze TTS 2 + Qwen3-TTS):HTTP API + MCP,供 agent 批量配音
Apache-2.0 -
Native macOS Qwen3-TTS speech studio, voice cloning, dialogue, and local HTTP/MCP service. Swift and MLX; MIT licensed.
MIT ★ 1 -
面向中小学交互式课堂的多智能体 AI 助教平台:Vue3 + Element Plus + uni-app + FastAPI + LangChain + Chroma + 硅基流动 Qwen3-VL + MCP工具。
MIT ★ 2 -
@cqsjjb/mcp-qwen-vl-plusupdated this year
MCP server for Qwen3-VL-Plus vision model - 支持图片上传和分析功能
npm MIT -
让 DSH 真正看视频的本地 MCP:VideoChat3/Qwen3-VL 视觉描述 + Whisper 语音转写 + 时间戳关键帧,三路独立证据交给决策模型核实。Windows, Python 3.13
MIT ★ 1 -
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 -
momofishgithub.com/tu95/momofishupdated this year
MoMoFish (摸摸鱼): Android MCP camera monitor for Claude Code with local capture and optional on-device Qwen3-VL/MNN inference.
★ 1 -
Local hybrid search for Korean Markdown notes & Obsidian vaults (BM25 + Hangul bigram + Qwen3 + rerank, MCP/CLI/SDK) · 한국어 마크다운 로컬 검색
npm MIT -
A local knowledge base for AI agents. Search, cite, and manage documents through MCP, with Qdrant, Qwen3 embeddings, and a web UI.
MIT -
Odinfer — a high-efficiency local inference engine for Qwen3.5-class models on Apple Silicon (MacBook Air first). Dense + MoE (35B-A3B family), MCP/HTTP server, zero-compile binaries, pure Odin.
MIT ★ 5 -
A local Vision MCP server for any MCP client, using Qwen3-VL through an external llama-server. One secure image-inspection tool over stdio or Streamable HTTP.
MIT -
A private voice studio for your computer: text to speech, voice design and voice cloning with open-source AI models (Qwen3-TTS). Built-in MCP server for AI agents.
Apache-2.0 -
mcp-anseractive
Universal 245K local Qwen3.8-27B Anser agent microkernel & MCP server: collaborative Socratic pair-programming, native multi-provider research (Brave, Tavily, Context7 docs, SearXNG, DuckDuckGo), cooperative landing turn ceiling preservation, in-process s
npm AGPL-3.0-or-later -
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 -
vision-mcp-nodeupdated this year
MCP server: 直连远端多模态模型 API 识别图片/OCR(OpenAI 兼容,如阿里云百炼 qwen3-vl-plus / qwen3.7-plus),不经过本地代理
npm MIT -
A coding agent built from scratch (no framework) that fixes failing tests in a locked-down Docker sandbox. Benchmark of validated bugs injected into toolz and boltons; structured tools beat bash-only 33% vs 8% (p=0.022) on local Qwen3-8B. Runs free on Ollama. MCP server included.
MIT -
LoRA fine-tuned Qwen3-1.7B for multi-hop QA: hybrid retrieval + reranking, iterative search, MCP server, OpenTelemetry. Matches Qwen3-8B on HotpotQA (EM 10.4 → 58.4) at ~8× the throughput.
MIT -
Законы и кодексы, mcp, cli, qwen3-emb-onnx
BSD-2-Clause -
qwen-video-blaxel-mcpgithub.com/adamanz/qwen-video-blaxel-mcpupdated this year
MCP server for video understanding using Qwen3-VL on Blaxel H100 GPUs
-
logoMCPgithub.com/gofastercloud/logoMCPupdated this year
MCP server for LLM-based brand design system generation — local Flux + Qwen3 on Apple Silicon
MIT -
vision-mcp-servergithub.com/Loveacup/vision-mcp-serverupdated this year
MCP server providing multimodal vision capabilities via OpenAI-compatible API (Qwen3-VL, GPT-4o, etc.)
MIT ★ 20 -
mcp-hydrocoder-visionactive
Vision MCP Server for Claude Code - Qwen3 VL 4B integration
npm MIT -
qm-image-parse-mcpupdated this year
视觉理解 MCP Server - 基于阿里云百炼 qwen3-vl-plus 模型的图像和视频分析能力
npm ISC -
forge-mcp-servergithub.com/arkad171717/forge-mcp-serverupdated this year
MCP server for dependency-ordered repository ingestion via qwen3-repo
pypi Apache-2.0 -
Create a Chatbot using Ollama, qwen3, gemini web search project, MCP server/client by creating tools.
-
Local CrispASR transcription for Codex and MCP agents. English via Cohere, Chinese via Qwen3-ASR 1.7B.
pypi MIT ★ 1 -
chat-mcpgithub.com/rocnubie/chat-mcpupdated this year
Qwen Chat (qwenchat.online) is a browser-based workspace for interacting with Alibaba's Qwen3 family of language models.
MIT -
gyy-mcpgithub.com/yourusername/gyy-mcpupdated this year
A FastMCP-based MCP tool with image recognition using Ollama qwen3-vl:8b model
pypi MIT -
Unified STT/TTS MCP server — WhisperX transcription + Qwen3 TTS, record/transcribe/speak tools.
MIT ★ 1 -
Local songwriting tools with your own soft rhyme rules. English lyrics, pinned Qwen3.5-9B, CLI/Python/MCP.
GPL-3.0 ★ 1 -
nanolensupdated this year
CLI + MCP tool for image analysis — ZAI (GLM-4.6V), Kimi (K2.5), GitHub Copilot (gpt-4o), Alibaba (Qwen3.5)
npm MIT -
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 -
Private AI platform on k3s — Ollama/Qwen3 + Milvus RAG + MCP agentic tooling + Fleet multi-cluster management
★ 1 -
MLX-Powered Agentic RAG System implementing Anthropic's Code execution with MCP pattern, featuring Claude Code hooks, skills, and MLX acceleration with Qwen3-VL-2B-Thinking for enhanced reasoning
-
MCP server providing long-term memory for AI agents — knowledge graph with Qwen3 embeddings, continuous learning, and knowledge evolution
MIT ★ 6 -
Hacker News 'Who is hiring?' ilanları için MCP sunucusu (FastMCP) ve Qwen3 ile araç çağıran iş fırsatı ajanı
MIT -
RAG policy Q&A agent demo (fake data): MCP server + n8n + Qwen3-8B, with an eval-driven improvement loop
MIT -
MCP server for delegating coding tasks from Claude Code to a local/LAN Ollama instance (Qwen3)
MIT -
Local-first production-style RAG system with hybrid retrieval, grounded Qwen3 generation, traceable citations, evaluation, FastAPI, MCP, Docker, and CI.
-
MCP server that lets AI assistants call the GoHumanize Open Humanizer, an open Qwen3-4B fine-tune that rewrites AI-styled English prose into more natural human writing.
npm Apache-2.0 ★ 1 -
Local OpenAI-compatible embeddings and reranking on Apple Silicon: bge-m3 hybrid search, Qwen3, a retrieval eval harness and MCP memory for agents.
MIT ★ 1 -
Text-to-SQL demo on fake app metrics (local Qwen3-8B): code-side entity linking, safe SQLite exec, summary number check, MCP server, eval-driven improvement loop
MIT -
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 -
dsh-luma-visiongithub.com/fuzzysoul/dsh-luma-visionupdated this year
Vision bridge for DeepSeek Harness (dsh): image understanding for text-only models via luma-mcp, free Qwen3-VL-Flash by default. 视觉理解插件:让纯文本模型获得看图能力(截图/报错/OCR/UI 分析)。
npm MIT -
Alexa+-inspired AI travel assistant that recommends outfits and packing lists from live weather data, using a self-hosted MCP server and Ollama (Qwen3:8B).
MIT -
Evidence-first MCP system for adaptive context selection over enterprise-style data, with governed retrieval, Qwen3-4B evaluation, robustness diagnostics, and reproducible evidence.
-
coreforge-media-mcpactive
MCP server for CoreForge media and local-model services: speech-to-text, document parsing (Granite-Docling), page-to-markdown, translation (MADLAD-400), embeddings and reranking (BGE), LLM inference (Qwen3-8B) and draft image generation (FLUX.1-schnell) —
npm MIT -
Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.
MIT ★ 66 -
本项目是一个 **MCP(Model Context Protocol)视觉服务**,核心用途是:**给 Opencode调用的DeepSeek模型配置视觉(Vision)能力**。 由于DeepSeek 模型本身不支持图像输入,因此本项目作为一座"桥":当 DeepSeek(通过 opencode 使用)需要分析图片时,会调用本项目的视觉工具;服务端收到请求后,将图像转发给支持视觉的低成本模型(例如:SiliconFlow 的 Qwen3.5 或Opencode Zen 的 mimo v2.5),再把分析结果返回给 DeepSeek。使得DeepSeek 拥有了"看图"的能力。
MIT -
An AI agent whose output becomes state only after a schema, a policy, a grounding check and, where required, a person. LangGraph + MCP + FastAPI + PostgreSQL outbox + Next.js review UI, measured on qwen3:8b.
Apache-2.0 ★ 1 -
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.
-
local-asset-gen-mcpgithub.com/davidemodolo/local-asset-gen-mcpupdated this year
Local AI asset generation MCP server: end-to-end text-to-image/audio/speech and image/text-to-3D with Qwen3-TTS, Stable Audio Open, SSD-1B, and TripoSR.
GPL-3.0 ★ 3