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

MCP Guard secures your MCP client from prompt injection attacks and more.

A Model Context Protocol (MCP) server for OpenSCAD 3D modeling and rendering

An MCP (Model Context Protocol) server that exposes every pybag Windows debugger function as a native MCP tool.

A Model Context Protocol (MCP) Server for Substack enabling LLM clients to interact with Substack's API for automations like creating posts, managing drafts, and more.

Persistent memory, XP evolutions, 21 species, and context-aware feedback for Claude Code CLI, Codex CLI, Gemini CLI, Copilot CLI, Cursor CLI, Openclaw, and other MCP-capable clients.

ProcmonMCP is a Model Context Protocol (MCP) server that allows LLMs to autonomously analyse . It exposes a comprehensive set of analysis tools to any MCP-compatible client, including Claude Code,...

A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database.

Turn any SQL database into a secure REST API. One binary. One command.

: A Model Context Protocol (MCP) server for integrating AI agents with Skywalking OAP and the surrounding ecosystem.

MCP server providing 28 UX knowledge resources, 23 analysis tools & 4 workflow prompts. Works with Claude, Cursor, Continue.dev, Cline, Zed & any MCP client.

MCP server for administering a Zigbee2MQTT estate: health reporting, mesh diagnostics, OTA updates, pairing, binding and device options over the MQTT bridge API.

is a Cursor-like AI agent for Google Earth Engine. It can be used right in your browser as a Chrome extension or through MCP server support.
Agent Skills

Speedily search and merge log messages by datetime

Make AI text sound like a real person wrote it. One Markdown file. 53 patterns, 5 voices, zero setup, and nothing leaves your machine.

Набор скиллов для работы с 1С:Элемент для AI агентов

这里放的是我希望 Agent 长期带着走的工作流:能触发、能执行、能验证、能复用,而非临时 prompt 或一次性脚本。

Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.

Sign in with Agent

Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subagents, skills, hooks, commands & MCP configs.

Slides AI Plugin for Claude, OpenClaw, etc that turns any idea into a full presentation — animated HTML or editable PowerPoint — from a single prompt

Comprehensive Java code health analyzer that scans for security, performance, correctness, and architecture issues. Outputs a 0-100 score with actionable diagnostics.

Claude Code skill for AI video & image generation via agent-media CLI

Bring Galileo powered eval workflows into Claude Code and Codex.

每个 Skill 是一个 Markdown 文件,被 AI 编程助手(如 Trae、Cursor、Copilot 等)加载后,能够引导 AI 正确完成嵌入式开发任务——从环境搭建、项目创建、编译、烧录到调试,全链路覆盖。