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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
Autonomous closed-loop multi-agent HVAC control system & digital twin sandbox using EnergyPlus 23.2.0, Qwen2.5, and MCP tools. Cuts peak power load by 13% while enforcing PMV thermal comfort bounds.
-
vl-mcp-serverupdated this year
VL 视觉理解 MCP 服务 - 基于 tokendance 的 Qwen2.5-VL 模型
pypi MIT -
aero-refgithub.com/georgejinu-labs/aero-refupdated this year
Multi-server MCP agent: AeroAPI live flight data + BigQuery catalog, orchestrated with LangGraph and Ollama local inference. FastMCP · mcp-use · qwen2.5
★ 1 -
Parlaygithub.com/sh4shv4t/Parlayupdated this year
Parlay — RL negotiation environment where LLM agents learn game theory, theory-of-mind, and strategic bluffing through self-play. OpenEnv compliant · MCP ready · GRPO-trained on Qwen2.5.
★ 1 -
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.
-
Multi-backend GGUF vision-language inference engine (moondream3.1 · VideoChat3 · Qwen2.5-VL · MOSS-VL · VideoMAE/ViViT · SmolVLM) with a unified CLI, Web UI and an MCP server for agents.
NOASSERTION ★ 4 -
Local AI agent with MCP tool calling: a FastAPI service asks an Ollama model (qwen2.5) which tool to use, runs it on a local MCP server over SSE, and answers from the result. Python · LangChain · MCP
★ 2 -
CodeBraingithub.com/Tschonsen/CodeBrainupdated this year
An MCP server that offloads bulk work from Claude Code to a local LLM (Qwen2.5-Coder 14B via Ollama). Claude stays the reasoner; the local model takes the bulk drafting, polishing, and explanation work to free up rate limits and context budget.
MIT ★ 1 -
PentestAIgithub.com/mhmdtaha091/PentestAIupdated this year
Autonomous web-pentest agent on consumer hardware — LangGraph + 23-tool MCP server + HippoRAG knowledge graph, driving a fine-tune-free Qwen2.5-Coder-14B on 12GB VRAM. Clears every Low/Medium module and 84.6% at High on DVWA.
NOASSERTION ★ 1 -
ai-flight-agentgithub.com/batikanakdenizz/ai-flight-agentupdated this year
Conversational flight agent: a local qwen2.5:7b picks a tool, MCP carries the call over stdio to query_flights / buy_ticket / check_in, and those drive a .NET airline API behind an Ocelot gateway on Azure.
MIT -
Graph-Augmented Code Intelligence RAG engine pairing deterministic AST call graphs with dense vector search to boost direct-callee Recall@8 from 0.0% to 53.3% (+53.3 pp) under a 5.8ms p95 latency bound. Powered by a QLoRA fine-tuned Qwen2.5 adapter (70.02 CodeBLEU), quality verification harness, and production Model Context Protocol (MCP) server.
MIT -
依 Model Context Protocol 實作 local-first 委派伺服器:7 個 tools(6 純本機加 1 個需另設金鑰的 opt-in 雲端搜尋)、1 個 resource 與 2 個 prompts,支援 stdio 與 Streamable HTTP、Bearer API Key 驗證與 map-reduce 摘要進度回報,並完成四家 client 實測。RTX 4090 上 1,332 字長文摘要 Qwen2.5-3B 0.63s、TAIDE-8B 1.21s
MIT -
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 -
🎯 Focused MCP Server - AI规划质量预测与优化 | 专注解决AI生成开发规划质量不稳定的核心痛点
npm MIT -
journey-agentgithub.com/github-hc/journey-agentupdated this year
Intelligent travel planner, capable of reasoning over real-world railway APIs, dynamically using tools via the Model Context Protocol (MCP), and orchestrating complex capabilities to generate accurate travel responses
★ 1