Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

An MCP server for exploring Israeli government open data (data.gov.il) — with built-in interactive visualizations powered by MCP Apps.

No Microsoft Graph API, no Entra app registration, no OAuth tokens — just your local Outlook and the authentication you already have.

PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human

Universal AI Tool Orchestrator - Sync skills, MCPs, and memory across Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw...

Persistent memory system for agentic AI via MCP - remember, recall, forget with semantic search with knowledge graph

Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.

Enhanced note taking for AI Agents with supervision.

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排, 配合大语言模型, 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes.

This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:

Tell your AI to demo your app. Pagecast records the browser, tracks every click and keystroke, and exports a shipping-ready GIF or MP4 — with tooltip zoom overlays and cinematic pan effects.

Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation
Agent Skills

一款基于 Taro 框架开发的多端 UI 组件库

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal.

Official Sketch Plugin directory

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Edit videos with coding agents

这是一个领域无关的 AI Context 工作区模板,用于为任意类型的多轮 AI 协作提供稳定、可追踪的上下文结构。

"Where'd you get that prompt?! It's lovely!" "Oh, this old thing? I got it at JeffreysPrompts.com."

tdoc is a prompt-native document surface for agent-assisted writing and review. It creates versioned HTML snapshots, adds Google-Docs-style comments on text and artifacts, and lets an agent pull...

Slides from Anything is a local-first presentation agent workflow for turning source material into delivery-ready decks.

A monolith for your agent's loop. Silent until it talks back.

一个 Claude Code skill(Codex 用户经 AGENTS.md 同样可用): 把你拍的照片蒸馏成极简 zine 纸质海报——手写 HTML/CSS/SVG、无头 Chrome 渲染。 不用图像生成模型,成品里没有一个照片像素。

Unofficial Python CLI for Google Flow. Drive Veo (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.