Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
MCPSafari: Native Safari MCP Server for AI Agents
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
- Let AI assistants analyze binaries directly
Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.
一款面向 的跨平台桌面工具。把提示词模板、自定义 Prompt、第三方 API 供应商、会话同步、Skills / MCP 和 TOML 配置都放进可视化界面里，不用反复手改文件。
An MCP server that lets AI agents read and draw on the Figma canvas — safely. Paired with a Figma plugin, it provides structured verification, safe-by-default drawing, and resilient multi-window...
A domain harness for AI-assisted mobile development and testing. Unified device logs, network traffic interception, and UI automation — exposed through APIs and MCP tools that let AI agents...
pixiv-cli brings the Pixiv ecosystem to the terminal: discover works and creators, manage accounts and collections, follow artists, bookmark artworks, and download visual works.
An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result
188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.
This project is a for automating and managing interactions on a Facebook Page using the Facebook Graph API.
Please see the updated mcpb format Claude Desktop Extension
Agent Skills
🚀 OpenManus-Max An Advanced Autonomous AI Agent Framework with Multi-Level Permissions & Trust Attenuation
A flexible and powerful AI agent library for Python, designed to build agents with tool support, multimodal capabilities, and streaming responses.
A collection of advanced agentic tools, skills, and workflows designed for the Antigravity AI coding assistant.
面向中文用户的 。项目基于 learn-claude-code 的 Agent 工程思路改造，用 Python + Aliyun DashScope/Qwen 实现一个只读 PR Review Agent：读取 Git diff 和 PR 描述，组织多个 reviewer 生成候选问题，再通过 debate loop 对 finding...
- : write in rich text or raw Markdown, switch anytime - : fully Obsidian-compatible - : a daily capture stream for quick notes, accessible from anywhere - inspired by Raycast: find anything as you...
A tiny skill that surfaces relevant terms of art as you work with agents, growing your domain vocabulary over time
一个可开新档的 AI 健身教练框架：训练记录、RPG 属性成长、剧情推进三者联动
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
macOS 可用 · Windows beta · DeepSeek API key · 非商业使用 English README
只需要一句指令，就能让 Codex 把 GPT Image 2 生成的美观图片转换为 PPTX；然后在 PowerPoint 中选择**或**，即可编辑重建后的各个元素。注意， 如果要编辑比较底层的元素可能需要多次的**，因为我们的重建逻辑涉及多层次的 元素组合。
adds rollback/recovery, adaptive context loading, and model routing intelligence on top of the original GSD by TÂCHES. Synced with upstream v1.24.0.
PhD students spend weeks on literature surveys. Most of that time is plumbing — finding papers, extracting claims, cross-referencing terminology, building comparison tables, chasing citation chains.