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.
-
Use qwen as a tool to power other CLI agentic LLMs
★ 3 -
qwen-memory-mcpgithub.com/John-CEO-HQ/qwen-memory-mcpupdated this year
Qwen-powered long-term memory for AI agents over MCP. Track 1 MemoryAgent hackathon submission.
MIT -
Local AI Excel analyst: MCP server, multi-agent pipeline and web chatbot powered by Qwen 2.5 on Ollama
★ 6 -
aegisops-autopilotgithub.com/Oxygen56/aegisops-autopilotupdated this year
Qwen-powered production incident autopilot with memory, custom tools, MCP integration, and human approval gates.
MIT -
qwen4deepseekgithub.com/zhen789/qwen4deepseekupdated this year
MCP server that gives DeepSeek and other non-vision models the ability to see images and read documents, powered by Qwen VL (阿里云百炼)
npm MIT -
Tetradgithub.com/SamoraDC/Tetradupdated this year
Tetrad is a high-performance MCP (Model Context Protocol) server written in Rust that orchestrates three AI-powered CLI code evaluation tools (Codex, Gemini CLI, Qwen) to validate all code produced by Claude Code.
npm MIT ★ 1 -
A powerful MCP server providing access to multiple AI models (Grok, Gemini, Kimi, Qwen, GLM) through OpenRouter. Perfect for Cursor, Claude Desktop, and other MCP clients.
npm MIT -
MCP server for AI-powered Minecraft mod development: files, Gradle, logs, crash-reports, screenshots and window control for IntelliJ IDEA workflows
MIT -
Production Qwen MemoryAgent for Thai rice/sugarcane farmers on Alibaba Cloud. 4-signal hybrid recall (vector + keyword + recency + reinforcement), LLM supersession, IoT alerts, pump HITL, MCP. Live on KhawTECH NaLog.
MIT ★ 2 -
M4-MCP-Agentgithub.com/carrey-Jin/M4-MCP-Agentupdated this year
A local-first, context-aware MCP server that gives Cursor persistent memory + private RAG, powered by Ollama.
MIT -
High-performance, calibrated non-autoregressive decision engine (<4ms CPU) powering dual-process agent reflexes, Antigravity IDE lifecycle hooks, MCP server, and OS automation.
-
The-Auto-PPT-Agentgithub.com/Arunika7/The-Auto-PPT-Agentupdated this year
AI agent that turns a single prompt into a fully designed PowerPoint - dual MCP servers handle research & design, powered by Qwen2.5-7B + Streamlit.
-
Little_MCPgithub.com/ricard1406/Little_MCPupdated this year
A simple yet powerful local AI Agent assistant that runs entirely on your machine. Option for remote LLM. Built for learning and deploy, Little MCP combines the power of open-source LLMs with advanced RAG that work with your personal documents. Included tools: real time weather, local documents RAG, local SQL database. Easy deploy your own agent.
MIT ★ 3 -
mcp-discord-assistantgithub.com/Jlassi-Mohamed/mcp-discord-assistantupdated this year
A powerful Discord management assistant leveraging the Model Context Protocol (MCP) and Ollama for local, privacy-first intelligence. This project provides multiple interfaces to interact with your Discord server, including a custom Streamlit dashboard and direct integration with Claude Desktop.
MIT