Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A Model Context Protocol (MCP) server that enables AI models to perform Android dynamic analysis using Frida.
一个功能强大的 Model Context Protocol (MCP) 服务器，基于 TypeScript 和 node-pty 实现持久化终端会话管理。即使客户端断开连接，终端命令也会继续运行，特别适合 Claude、Cursor、Cline 等 AI 助手执行长时间任务。 油管视频地址：https://youtu.be/nfLi1IZxhJs b站视频地址：https://www.
A Go implementation of the OData to Model Context Protocol (MCP) bridge, providing universal access to OData services through MCP tools.
Implementation of the paper: MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization
mcptools implements the Model Context Protocol in R. There are two sides to mcptools:
This is a server that lets your LLMs (like Claude) talk directly to your BigQuery data — . Think of it as a friendly translator that sits between your AI assistant and your database, making sure they...
A Model Context Protocol (MCP) server for querying the Shodan API and Shodan CVEDB. This server provides comprehensive access to Shodan's network intelligence and security services, including IP...
Transform any OpenAPI/Swagger definition into a fully-featured server – ready to run locally, inside Claude Desktop, or in the cloud.
This MCP server is made for study purposes with use of reverse engineered Rohlik API. It is for personal use only.
ReActMCP Web Search is an MCP (Model Context Protocol) server that integrates web search capabilities into your AI assistant framework.
O único servidor MCP com suporte nativo a NF-e, NFS-e, SPED, eSocial, Simples Nacional e Reforma Tributária 2026 (IBS/CBS) - sem conta, sem chave e sem configuração.
The minimum-overhead way to add AI commands to CesiumJS
Agent Skills
Most code review looks at how the code is written. The Quality Playbook looks at what the code is supposed to do, and whether it actually does it.
Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.
Codex pets are tiny ambient companions for the work happening in Codex. This project adds one more layer to that idea: your pet can quietly show how much Codex capacity you have left, without turning...
A portable framework that reduces the cognitive load of working with AI coding agents — plan, build, verify, milestone by milestone.
A synthesis of Claude Code best practices, aggregated from Twitter.
一个中文文案「去 AI 味」skill，可以在 CoPaw、OpenClaw、Claude Code、Hermes，或者任何能读取 SKILL.md 并执行本地 shell 命令的 agent 里使用。
OpenCode port of academic-research-skills: 4 skills, 13 slash commands, 38-agent pipeline for academic research, writing, peer review, and revision
Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files. Works as a Claude AI skill.
Direct work across Claude Code, Codex CLI, and Grok Build.
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.
*Tuned for (1M-token MSA context, native multimodal input) and (Agents Window, canvases, Design Mode, /worktree, /best-of-n, Await, MCP Apps). Written to stay useful across model changes.*
This is the official website for TuriX Computer-use-Agent