Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Run any agent — Claude Code, Codex, or holaOS — in one local-first workspace, over your tools, your files, and one shared memory. Frontier models built in, or bring your own keys.
Brings MCP to ChatGPT, DeepSeek, Perplexity, Grok, Gemini, Google AI Studio, OpenRouter, DeepSeek, T3 Chat and more...
70+ databases in 20 MB. Desktop, Docker, CLI, built-in AI assistant, and MCP Server.
A Model Context Protocol server that provides tools for interacting with Airtable's API. This server enables programmatic management of Airtable bases, tables, fields, and records through Claude...
A Model Context Protocol (MCP) server for Socket integration — lets AI assistants query dependency vulnerability scores and security metadata.
A Go-based server implementation for the Model Context Protocol (MCP) with Grafana Loki integration.
A Model Context Protocol (MCP) server that provides integration with Figma's API through Claude and other MCP-compatible clients.
DeepView MCP is a Model Context Protocol server that enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini 2.5 Pro's extensive context window.
Debug Electron apps from Cursor & Claude with real DevTools superpowers. Model Context Protocol server · Chrome DevTools Protocol · start / attach / screenshot / console / DOM / UI automation /...
A Model Context Protocol server that connects Twenty CRM with Claude and other AI assistants, enabling natural language interactions with your customer data.
This project is no longer needed. Ragie now supports MCP natively as a streamable HTTP server. See docs here: [https://docs.ragie.ai/docs/mcp-overview]
An enterprise-grade Model Context Protocol server for Power BI and Microsoft Fabric.
Agent Skills
Herdr Browser renders a real Chromium view inside a Herdr pane and exposes it to Chrome DevTools Protocol clients.
AI Skill tra cứu thuế TNCN, SOP kê khai/quyết toán, hướng dẫn theo nhóm đối tượng.
This skill makes an AI agent write in a plain style. The full rules are in SKILL.md.
— 基于 Claude Code Agent Teams 的多智能体协作安全分析框架
面向电商商品图生产场景的图片套图 Skill。仓库提供一套从商品图分析、卖点提炼、Prompt 组织到成图输出的脚本与配置，适合用在淘宝、京东、拼多多、抖音等国内平台，以及独立站、Amazon 等跨境场景。
An agent-oriented skill for turning an SVG into a hand-drawn animation deliverable.
— 使用、修改或部署本專案，必須標明原作者 、附上本 repo 連結，並以相同授權公開原始碼。網路服務部署亦同。 本專案於 2026/04/13 從 MIT 切換至 AGPL-3.0。此日期之前取得的版本仍適用 MIT 授權。
一个封装了产品经理核心思维的 skill，帮助非产品经理用户写出高质量的产品需求文档（PRD）。 A skill that encodes core product management thinking to help non-PM users write high-quality Product Requirement Documents.
humble A humble, and fast, security-oriented HTTP headers analyzer
LLM Wiki 是一种用 LLM 构建个人知识库的方法论。与传统 RAG（每次查询从头检索）不同，LLM 会**，知识随每次导入和查询不断积累，形成复利效应。
ATR (Agent Threat Rules) is an open detection rule format for AI agent security threats. Rules are written as YAML documents conforming to a versioned schema, identified by the public ATR-YYYY-NNNNN...
Turn any LLM into a deterministic World Cup prediction engine with one prompt.