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

A MCP server implementation for hyperbrowser

An MCP server that provides control over Android devices via adb

飞书/Lark官方 OpenAPI MCP

⚡ Blitz Strike — a universal MCP penetration-testing toolbelt. Structured methodology: reconnaissance & attack-surface mapping, source-to-sink analysis, and live validation.

🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️

基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server

Agent-native knowledge engine — search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX.

The local runtime, CLI bridge, SDK, drop-in adapters, and wallet/auth/signing layer are MIT and readable here, so you can verify what runs on your machine rather than trust a black box.

MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.

A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches and extract results.

Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform

Official Jina AI Remote MCP Server
Agent Skills

Agent skills for AI coding assistants (Antigravity)

Agent Skills 工具箱fetch-everything 一套面向 **Claude Code**/openclaw 的高质量 Skills 合集,涵盖网页抓取、文档提取、电商数据处理、云端部署等场景,特别强化了对中文平台的支持。

Build orchestration for LLM pipelines

Hermes Agent skill for typography-led lyric videos using GPT Image 2, Gemini Omni Flash, and exact-text QC

Agent skills that turn raw markdown notes into a self-updating LLM knowledge base

DeepSeek Harness (DSH) 插件精选目录 — 14 类 280+ 个社区插件,覆盖 MCP / Skill / TUI / 多 Agent / 上下文记忆 / UI 皮肤,点链接直达仓库。Curated directory of dsh plugins for DeepSeek Harness.

覆盖分类/回归、时间/分组验证、泄漏检查、模型比较调参、SHAP解释、稳健性分析,以及论文级图表、Excel和报告交付

Claude Code skill for s&box game development. Schema-verified API reference, 10 runnable examples, zero Unity hallucinations

Free H70-C+ Spark Skill Graphs guild for Codex visual builder loops with imagegen and vision.

Proactive security monitoring for OpenClaw deployments. Detects ClawHavoc, AMOS stealer, CVE-2026-25253, memory poisoning, and supply chain attacks.

A framework-agnostic, git-native standard for defining AI agents

科研写作助手 (Research Writing Assistant)