Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.

CLI MCP package manager & registry for all platforms and all clients. Search & configure MCP servers. Advanced Router & Profile features.

Obot is an open-source platform that provides everything an organization needs to implement MCP technologies.

Scan MCP servers for potential threats & security findings.

Allow AI to wade through complex OpenAPIs using Simple Language

You use Claude for some things, ChatGPT for others, and Cursor for code. But your context, including your projects, decisions, and preferences, does not move with you.

Native macOS client for Model Context Protocol (MCP)

LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing...

Easily spin up an MCP Server on Next.js, Nuxt, Svelte, and more

A comprehensive collection of Model Context Protocol (MCP) servers

Easily spin up an MCP Server on Next.js, Nuxt, Svelte, and more

MCP server for JADX-AI Plugin
Agent Skills

Make Codex pick the right skill or plugin more often.

100个精心策划的AI驱动自动化循环,覆盖软件开发、数据科学、内容创作、产品运营、学习管理等多个领域。面向中国用户优化,全中文文档与提示词支持。

A custom Claude Code skill: a strict for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms.

A Copilot CLI skill that analyzes your repository and generates the configuration files AI agents need to contribute correctly.

Practices, protocols, and skills for AI-driven software development

Multi-CLI plugin that orchestrates 49 AI agent personalities (start → plan → build → review → ship) across Claude Code, Codex, Cursor, Copilot, Gemini, Antigravity, Kiro, Windsurf, OpenCode, Kilo,...

▲ SEO Middleware • Web Analytics • Web CRON • WebSec • HTTP & SNMP Monitoring • ostr.io is a unified web-services platform

专为 优化的 Codex skill,大幅降低 token 消耗并提升前缀缓存命中率。

AI Unified Process (AIUP) is a requirements-first workflow for taking software from a product vision to reviewed specifications, implementation, and traceable tests.

Agent-native persistent knowledge management — compile knowledge once, query forever.

Agent Skills as a Memory Layer

Opinionated skills for AI coding agents to create stunning diagrams and visualizations directly in Markdown.