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
This MCP server provides read-only access to MySQL databases. It allows you to:
is an experimental MCP server for summarizing GitHub discussions, issues, and pull requests. Answer questions like:
Code Mode MCP — aggregate all your MCP servers behind search() + execute()
Bilibili 视频字幕/弹幕/评论提取 MCP Server — 扫码登录，自动提取字幕/弹幕/评论与元数据，输出结构化 Markdown 供 AI 理解
A Model-Context Protocol server for the MITRE ATT&CK knowledge base
gives AI agents a persistent, searchable memory they can use across sessions. V2.1 adds SQLite, full-text search, user-editable categories, safer Docker defaults, and verified backup-first upgrades.
VideoNote：将视频转成文字或笔记。理解画面/弹幕/评论；支持主流平台；工具解耦；多格式导出。
Free trending topics aggregator — 20 sources, zero auth. CLI + Python library + MCP Server.
Safe DOCX suite: docx-primitives, docx-comparison, safe-docx MCP server
小叶发布器：连接浏览器登录态与 MCP/AI 客户端，一键提取文章并保存到公众号、知乎、掘金、CSDN 等平台草稿箱，适合自媒体作者和开发者本地自动化发布。
An MCP server implementation that integrates with SearXNG, providing privacy-focused meta search capabilities.
微信 4.0 (Windows) 本地数据库解密工具。从运行中的微信进程内存提取加密密钥，解密所有 SQLCipher 4 加密数据库，并提供实时消息监听。
Agent Skills
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-agent operating system for Blender 5.2: skills, verified bpy knowledge base, AGENT_OK/AGENT_FAIL execution contract, production gate for 3D-printable parts, robot-arm demo
Your AI Becomes a Security Team. Every Language. Every Layer. Zero Tools.
A collection of AI agent skills for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.
Cross-border e-commerce AI knowledge base, designed to be read by people and installed by agents. 69 trilingual guides, 878 structured prompts, a 94-entity / 318-constraint domain ontology, and 9...
AI Unified Process (AIUP) is a requirements-first workflow for taking software from a product vision to reviewed specifications, implementation, and traceable tests.
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Your agent invents things because it has no memory, and can't touch your database because it has no arms.
Agent-native persistent knowledge management — compile knowledge once, query forever.
Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.
My Codex Skills
51 specialist AI agents for US healthcare administration. Installable prompts and skills for Claude Code, Codex, OpenCode, Cursor, Copilot, and other agentic coding tools.