Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
飞书 MCP 配置指南 - 让 AI 读写飞书文档、多维表格、知识库 | Feishu/Lark MCP for openclaw, Cursor, Claude Desktop
A powerful MCP server implementing sequential thinking protocol that provides a structured approach to problem-solving.
Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.
PyMOL plugin - drive PyMOL from Claude Code, Cursor, or any MCP client.
A powerful CLI + MCP Server for working with photos: search, edit, tag and describe photos right from the terminal.
AI‑powered YouTube uploader—no CLI, no YouTube Studio, and no secrets ever shared with LLMs or third‑party apps and all free of cost!
Connect Raindrop.io to your AI assistant with a simple MCP server. Use it to organize, search, and manage bookmarks with natural language.
mail-mcp Production-ready email MCP server for AI agents IMAP + SMTP + EWS + Microsoft Graph API — built in Rust
Your codex login → a full ChatGPT Plus/Pro account (every model, deep research, image gen, code exec) inside Claude Code, Codex & any MCP client. One-line install.
Universal Memory Protocol (UMP) - an open standard for agent memory. The third interop layer beside MCP (tools) and A2A (coordination).
Live through COM on Windows, or headless through ezdxf anywhere — one typed contract, two engines.
The jMRI (jMunch Retrieval Interface) specification — an open interface standard for token-efficient context retrieval in MCP servers.
Agent Skills
A comprehensive collection of skills for Claude Code, Anthropic's official CLI for Claude.
* * * — plus key rotation, cross-platform biometrics, and an encryption preflight
An iterative deep-logic security audit agent for Claude Code. Nemesis combines two complementary audit methodologies in an alternating feedback loop to find bugs that neither can catch alone.
No setup required · Works for any company or industry
ATR (Agent Threat Rules) is an open detection rule format for AI agent security threats. Rules are written as YAML documents conforming to a versioned schema, identified by the public ATR-YYYY-NNNNN...
humble A humble, and fast, security-oriented HTTP headers analyzer
is an AI Agent development scaffold Meta-Skill that establishes four layers of enhancement for any project in one command: knowledge management, architecture constraints, feedback loops, and entropy...
— 使用、修改或部署本專案，必須標明原作者 、附上本 repo 連結，並以相同授權公開原始碼。網路服務部署亦同。 本專案於 2026/04/13 從 MIT 切換至 AGPL-3.0。此日期之前取得的版本仍適用 MIT 授權。
虾说 ClawTalk — AI 小龙虾社交平台
No exports. No API keys. No paste-in data. Production-tested at InhouseSEO.
一份**（见 UNIVERSAL.md），给任意 AI 助手当「程序化工作流」使用，覆盖： 全生命周期。 适用于 Cursor、Claude、Claude Code、Cline、通义灵码、CodeBuddy、ChatGPT 自定义指令、WorkBuddy 等任何支持项目上下文 / 系统指令的 AI 工具。
面向电商商品图生产场景的图片套图 Skill。仓库提供一套从商品图分析、卖点提炼、Prompt 组织到成图输出的脚本与配置，适合用在淘宝、京东、拼多多、抖音等国内平台，以及独立站、Amazon 等跨境场景。