Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
An Mcp client inside Emacs
Intelligent token optimization through caching, compression, and smart tooling for Claude Code and Claude Desktop
现代化资产测绘与漏洞监控平台 (ARL-Next)。经典 ARL 架构重构，聚焦企业资产关联、异步解耦并发调度与原生 MCP 协议集成，容器化开箱部署。
Kubrick Course Hi Dave... Learn to build AI Agents that can understand images, text, audio and videos.
A simple web GUI to manage Model Context Protocol (MCP) servers for the Claude Desktop app on MacOS easily.
Discover the most comprehensive and up-to-date collection of MCP servers in the market. This repository serves as a centralized hub, offering an extensive catalog of open-source and proprietary MCP...
The open source integration platform for agentic AI. Connect any AI model to thousands of APIs, data sources, and tools with a single function call.
A Model Context Protocol server that enables LLMs to interact with MongoDB databases. This server provides capabilities for inspecting collection schemas and executing MongoDB operations through a...
Vulnerable MCP Servers Lab ==========================
This repository is a collection of guides, utilities, and server implementations for the created while learning MCP.
Own the context. Rent the memory. Your notes stay plain .md files you own — bring any AI model and swap it whenever you like.
Web research your agent can actually use. Quality-scored Google search, clean webpage extraction, and deep multi-source research for Claude — over the Model Context Protocol.
Agent Skills
The official, auto-generated awesome list for the Cordis plugin ecosystem — curated by cordis.run, the DeepSeek Harness plugin marketplace.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
Fast Rust-based bundler for the web with a modernized webpack API 🦀
A collection of interesting libraries and tools for Avalonia project.
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable, and resumable.
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.
A Context Engineering Framework for AI-Assisted Multi Agent Applications Development
An agent skill and command-line tool for controlling Chrome directly through the Chrome DevTools Protocol (CDP).
:rocket: The Ultimate Image Uploader for Efficient Creators. Supports Obsidian, Typora, VS Code etc. and 60+ image hosting services (S3, GitHub, Cloudflare R2, Imgur, Aliyun OSS...).
A collection of open-source skills for AI coding agents (Claude Code, OpenClaw, etc.) powered by the Pika Developer API.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration,...