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

Multi-tenant · Authenticated · Observable · Rate-limited · Cached · Circuit-broken · Governed

Grok Build plugin for Claude Code, Grok, Codex, Cursor and others. Provides /grok:search, /grok:review, /grok:rescue commands + grok_search MCP tool for live X/web search.

특허청 오픈API를 MCP 도구로 노출하는 서버. 특허·실용신안·상표·디자인을 키워드/항목/출원인/권리자로 검색하고, 출원번호로 상세 서지정보를 조회한다.

this is dynamic mcp server for runtime analysis and process hacking. it is like processhacker but for ai agents.

CLI, OpenAI-compatible API, Chrome extension bridge, and MCP server for Google Flow image and video generation.

CLI & MCP for GitHits - The Code Context Layer for AI Coding Agents

Access Kagi search and summarizer via session tokens — completely free. Works with Claude Desktop, Cursor, Windsurf, Cline, Hermes and any MCP-compatible AI coding assistant/agent.

Universal Memory Protocol (UMP) - an open standard for agent memory. The third interop layer beside MCP (tools) and A2A (coordination).

Give your coding agent the ability to design 3D models.

Self-hosted, ultra-light, zero extra effort for the people doing the work.

Use natural language to explore your organization's cloud costs via MCP clients, like Claude, Cursor, and others.

An MCP server that connects with your Apple Notes on macOS.
Agent Skills

🦄 Monads and popular FP abstractions, powered by Go 1.18+ Generics (Option, Result, Either...)

Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Pastebin on Cloudflare worker, with friendly CLI usage and rich features

An agent skill and command-line tool for controlling Chrome directly through the Chrome DevTools Protocol (CDP).

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

个人的pi Agent 配置仓库

A prompt-first starter kit for turning repeated coding-agent mistakes into durable repository instructions, checks, memory, and evaluation.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Stage-aware security skills for Codex that surface planning gaps, offer opt-in reviews, and help teams ship safer code without pretending to certify security.

Repository for skills to assist AI coding agents with .NET and C#

MBA AI Agent课程:2天集中培训,从LLM基础到多智能体系统