Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
An MCP server that slurps data from Google News and Google Trends RSS endpoints, optionally distills it with LLM/NLP, and barfs out structured results.
A browser extension and MCP server that allows you to interact with the browser you are using.
Illustrative estimates. The ~90% is Claude-side token reduction on analysis-heavy tasks — not total cost: Kimi's own subscription still applies.
MCP proxy server that filters tools from upstream MCP servers via regex-based deny list
mcp-repl is an MCP server that gives an agent a persistent Python or R session, kept alive across tool calls.
The TypeSpec MCP Server implements the MCP specification to enable you to quickly build out your own MCP servers powered by TypeSpec.
mcp-difyworkflow-server is an mcp server Tools application that implements the query and invocation of Dify workflows, supporting the on-demand operation of multiple custom Dify workflows.
MCP server for integrating LightRAG with AI tools. Provides a unified interface for interacting with LightRAG API through the MCP protocol.
Reqable MCP Server is a Dart-based MCP server that communicates with AI tools over stdio and exposes Reqable capabilities through MCP tools.
Public MCP Server README: capability boundaries, auth, install, and dangerous-tools disclosure.
OnebotV11 Bot as MCP Server.
This monorepo contains MCP (Model Control Protocol) servers for different services.
Agent Skills
The definitive list of agent skills and template libraries for generating beautiful, single-file HTML presentations — for Claude Code, Codex, Cursor, OpenClaw, and Hermes.
Split "planning by chatting with an agent" from "visualizing + executing" into two independent modules:
基于 Andrej Karpathy 提出的 LLM Wiki 模式 构建的 Agent Skill，通过四阶段流水线将碎片化信息转化为结构化、可检索、持续增长的个人知识库。
On agent | Claude Code, Codex, OpenCode, Antigravity, Copilot, Cursor, Grok-Build, Pi, Hermes, OpenClaw, etc.
A complete development workflow for AI coding tools
A Python framework for modular, self-contained skill management for machines.
CODING — a local-first AI coding agent for repository-aware planning, execution, validation, and delivery.
Trending Claude Code skills
文档语言 / Readme language 中文 · English · 日本語
An open-source security playbook for AI agents. Structured, OWASP-grounded procedures that enable agents to perform security engineering tasks — from code review to AI agent security audits.
Blender-to-browser workflow, Codex skill, and interactive Three.js hero examples with editable source assets.
audit-prompt-caching is a portable Codex/agent skill for finding why LLM cache reuse fails across the request path: prompt/prefix caches, provider cache telemetry, cache-aware routing, agent tool...