Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
A focused, type-safe that lets Claude Code (or any MCP-compatible client) drive a locally-running application — read chart state, change symbols and timeframes, fetch OHLCV bars, capture screenshots.
AI 에이전트에게 라고 말하면, 흩어진 자료(웹 링크·PDF·대화 로그·텍스트)를 **하고, 관련 있는 노트끼리 **하고, **하고, **까지 해 주고, 원하면 **해주는 **이에요. (Codex엔 "플러그인 설치(/plugin)"가 없어서, 대신 저장소를 받아 codex mcp add로 **해 연동해요.)
Python implementation for building Users Management Agent with MCP tools and MCP server
MCP Server for integrating Codex CLI into Claude Code workflows with session management and real-time progress monitoring.
DeepSeek Harness MCP Connector: connect servers, search tools across active connections, and troubleshoot discovery. Includes a continuously updated catalog; supports OAuth 2.
A Flutter MCP to interact with your flutter app
An experimental way to connect MCPs to Pi using Code
MCP server that lets Claude Code pause mid-task and ask a human a question via Slack — then resume once you reply.
A protoc plugin for generating mcp servers in golang from a protocol buffer specification
An MCP server demonstrating Claude Shannon's systematic problem-solving methodology. This server provides a tool that helps break down complex problems into structured thoughts following Shannon's...
MCP proxy server that filters tools from upstream MCP servers via regex-based deny list
windbg-mcp-rs is a pure WinDbg extension DLL that exposes the current debugging session as an MCP server.
Agent Skills
Local-first AI agent framework built for small models, with optional hybrid cloud support.
Watch the skill in action — generating a complete 64×64 character spritesheet from a single prompt:
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.
MyCodeAgent is a local-first, single-agent Python coding harness. It supplies the reliable machinery around an OpenAI-compatible model: one controlled loop, project-confined tools, permission...
Spawns 8 parallel specialist agents to audit your codebase across vulnerability detection, authorization verification, secret scanning, supply chain analysis, IaC security, threat intelligence...
A self-improving prompt optimization skill for Cursor and Claude Code, derived from Andrej Karpathy's autoresearch pattern.
This is where the real-time thinking happens: arXiv category coverage, eval design, prior-art hunting, and neurodivergence-inspired research on reasoning architectures — shared with the ADHD...
CashClaw The Agent Economy Layer — agents earn, agents spend, Guard protects.
A library of healthcare and life sciences domain capabilities — reference agents with best practices, reusable skills, and MCP-based tools — serving builders in their IDEs, researchers in Amazon...
A Claude Code skill that enables AI-assisted generation of macOS/iOS Shortcuts. Create valid .shortcut plist files that can be signed and imported into Apple's Shortcuts app.
使用 LangChain 1.0 构建的 Skills Agent，演示 Skills 三层加载机制的底层原理。默认使用 Anthropic，也支持 OpenAI / OpenAI-compatible 接口。
You found an amazing open-source project and want AI to help you understand and work with it, but faced these problems: Too much code for AI to read? Complicated configuration AI can't handle?