Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A Model Context Protocol (MCP) server for Intervals.icu integration. Access your training data, wellness metrics, and performance analysis through Claude and other LLMs.
The most comprehensive Model Context Protocol (MCP) server for GitLab — 86 tools, enterprise-ready, actively maintained.
An experimental Model Context Protocol (MCP) server that bridges Granola.ai meeting intelligence with Claude Desktop.
A Model Context Protocol (MCP) server implementation powered by txtai, providing semantic search, knowledge graph capabilities, and AI-driven text processing through a standardized interface.
A Model Context Protocol (MCP) server for X (Twitter) integration. Provides 26 tools for reading timelines, posting, searching, engagement (likes, retweets, bookmarks), user lookup, follower export,...
Built by Thomas Monk , London School of Economics.
A Model Context Protocol (MCP) server that provides debugging capabilities through the Debug Adapter Protocol (DAP).
A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through IoTDB.
is a Model Context Protocol (MCP) server that connects AI agents with the Zscaler Zero Trust Exchange platform. for security, requiring explicit opt-in to enable write operations.
This is a Model Context Protocol (MCP) tool that allows Claude to interact with Microsoft Outlook for macOS.
A JetBrains IDE plugin that exposes an , giving AI coding assistants full programmatic control over the debugger.
Model Context Protocol (MCP) is a standardized protocol for managing context between large language models (LLMs) and external systems.
Agent Skills
Skill from : How To Use The Hedge Fund Method To Win Every Single Trade.
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.
这个库的旨在为同学消除选择课程，学习资料等信息差。 在大学中存在大大小小的信息壁垒，然而要打破这些壁垒获取情报却要耗费大量时间精力。 有时上完一节课才意识到应该如何去上这门课，但为时已晚，学习结果可能不尽人意留下遗憾。 为了将那些不确定的，流状态的，短暂的，难以获取的，口口相传的信息保存下来，我们建立了这个库，希望能帮助到大家。 （摘自浙江大学课程攻略共享计划）
上周写了一篇文章，与 AI 一起做产品的六条原则，很多朋友都喜欢这套插图，问我怎么做，就把它做成 skill，开源发布。
This skill is maintained as a standalone submodule of Kernel Design Agents (KDA) for easy installation.
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.
Creates Claude Code skills with built-in best practices from Anthropic's official documentation.
A simple CLI for orchestrating Claude Code, Codex, and OpenCode.
把 deepseek-v4-flash 或 deepseek-v4-pro 注册为 Codex 原生自定义子 Agent，并验证实际派发路由。DeepSeek V4 Pro 的 8·13 更新继续使用 deepseek-v4-pro API 标识。
基于 OpenClaw 的论文自动检索、总结、评估智能体框架。 可为任意研究领域生成专门的论文专家智能体。
Declarative Agent Workflow Framework For individual developers and teams, build, debug, deploy, and continuously strengthen your own Claw capabilities
Kilroy is a local-first CLI for running StrongDM-style Attractor pipelines in a git repo.