Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
The Meshery MCP Server extension - an MCP server that streamlines and accelerates creating Meshery designs
Self-hosted Puppeteer MCP server with remote SSE access, API key authentication, and Docker deployment. Complete tool suite for browser automation via Model Context Protocol.
A MCP Server that provides browser access through playwright with "stealth mode" enabled.
MCP-SafetyBench is a comprehensive benchmark designed to systematically evaluate the safety and robustness of LLM agents operating in the Model Context Protocol (MCP) ecosystem.
Omnigentx Jarvis — voice + chat AI assistant powered by Fast Agent (MCP) with Vue dashboard. Single-user, self-hosted, multi-skill orchestration.
Lighthouse for MCP — score any MCP server 0–100.
A collection of MCP servers for connecting real-world tools and data to LLMs.
one go multi-agent system like manus using any MCP you want with configuration // 一个go语言编写的类似manus的多智能体系统，可以通过配置连接任何你想使用的MCP组件
💫 Tachyon MCP Runtime for Java and Kotlin - Model Context Protocol (MCP) server with Streamable HTTP, native Netty transports, tools, tasks, resources, prompts, completions, resumable sessions, and...
An example of the Epic Stack with a /mcp endpoint
Yet another minimal MCP server for Unity
LLM Gateway to call 100+ LLM APIs in OpenAI format with MCP supported.
Agent Skills
An agentic mobile security research system built as a Claude Code project. An orchestrator spawns focused sub-agents, each with one narrow objective.
Developer API error catalog: codes, HTTP, causes, next steps.
마크다운 노트를 RDF/TTL 지식 그래프로 변환 - SPARQL 질의로 시맨틱 검색
雅思自学 skills，用于搭配 ClaudeCode 自学雅思，功能丰富好用
This is the hands-on sample for the workshop. It is — it ships the CloudFormation template (cfn/workshop-infra.
Practical small-team release-day checklist: D-1, go-live, monitor, comms, rollback owners.
交互式中文经济学实证论文自动化工作流 — 从选题到排版成文的全流程 Skill
Efficient multi-strategy Zotero search using code execution pattern
VLA Expert Skill 一键让你的 AI 编程助手变成 VLA 领域专家。它解决两件事：1. 注入 332+ 篇论文的压缩知识——不是摘要，是拆解后的工程细节、架构选择、训练配方。2. 内置对抗性思考纪律——每个判断都经过双向取证、来源分级、可证伪检验，不让 AI 输出正确的废话。每天早上自动更新。
Deep Skill Finder – Find the right Skill for every Agent task
AI 戰場編輯器 — 資料驅動的單檔 3D 戰場引擎;每場戰役是一份 package(赤壁、官渡、垓下、淝水範例)
OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.