Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
MCP server with runtime-level tools for Phoenix development
Secure, audit, and govern every AI API call and MCP tool invocation across your organization — from a single control plane.
Evidence from your and sources (GitHub repos, PRs, npm). One toolset: ripgrep + AST search, trees, precise reads, and LSP — as a or , backed by a for fast, token-efficient results across single files...
A single agent thinks. A collective decides. We're building the swarm.
Fetch · crawl · bypass bot walls · read PDFs (even scanned) · search the web One MCP server · one warm browser · zero accounts · runs on your machine
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
A flexible multi-interface AI agent framework that can interact through various platforms including Telegram, Discord, Twitter, Farcaster, REST API, and MCP.
MCP server and CLI tool for searching and downloading documents from Anna's Archive
Instead of relying on one-off scripts generated for a single question, analysts and AI agents can use tested analytical primitives and reusable workflows to inspect customer journeys, explore...
Local code intelligence MCP server and CLI for AI coding agents
Auto Browser is an MCP-native browser control plane for authorized workflows. It gives MCP clients, LLM agents, and operators a shared Playwright browser with human takeover, reusable auth profiles,...
Real websites for your coding agent to learn design from, searchable over MCP.
Agent Skills
AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, and galleries with intelligent layout and AI-generated content.
A fast, browser-only diagram tool (think a tiny Figma/Excalidraw). Draw shapes, connect them with auto-snapping lines, drop in icons, and everything auto-saves locally.
A plugin for consulting distilled personas of colleagues — locally, without involving them. Useful for pressure-testing plans, anticipating pushback, or stress-testing decisions through someone...
AI agents are powerful. They're also stateless, pattern-matching tools that will confidently build the wrong thing if you let them.
Agentic chat runtime where markdown is the protocol
Lets an AI agent (Claude Code, Codex, etc.) query the user's locally-running desktop app over its built-in HTTP API.
在本项目开始筹办之初，对于所有 SII 的学生，启智平台是科研实验链路里最慢的那一环：每次申请资源、新建 Notebook、新建训练任务、同步代码都要反复点点点，SSH 等更进一步的功能更是遥遥无期。
Jianing 的公开 Skill 合集仓库。每个一级目录都是可独立安装、独立触发的 Skill；合集仓库只负责统一发现、安装和版本管理，不把所有能力塞进一个巨型 SKILL.md。
— covering both the and tiers of Anthropic's Claude Certified Architect program.
A skill that creates, evaluates, and improves other skills. Meta-level.
Type 中文, CC sees English. Sidecar i18n proxy for Claude Code.
A curated collection of Claude Code skills for professional AI-assisted workflows.