Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A Model Completion Protocol (MCP) server implementation for ServiceNow, allowing Claude to interact with ServiceNow instances.
An Obsidian-native memory layer for your AI agent. Plain Markdown you own, in the same vault you already use.
Local-first MCP platform with OAuth2 for running and monitoring your servers
Operate Proxmox VE from MCP clients, AI agents, and OpenAPI tooling through one security-conscious control plane for VMs, LXCs, snapshots, backups, ISOs, container commands, and persistent...
Pro Tip: You can use this to ask your agent to export the 3d model directly into the project you are working on to use them in your app instantly. Demo
An MCP server that provides access to arXiv papers through their API.
An MCP proxy server that aggregates and serves multiple MCP resource servers through a single interface. This server acts as a central hub that can:
An MCP server that connects your AI assistant to HackerOne. It pulls your bug bounty history, program scopes, and report details into a local SQLite database, then exposes tools that let any...
MCP server for enabling LLM applications to perform deep research via the MCP protocol
MCP server for rendering Mermaid diagrams in Claude Code with functionality and a built-in skill for expert guidance.
An MCP server to use with AI agents such as OpenCode, Mai, VSCode, Claude, CLION, ...
An MCP server that automates WeChat on macOS using the Accessibility API and screen capture. It enables LLMs to interact with WeChat chats programmatically.
Agent Skills
AI assistant for Obsidian with , , and powered by Google Gemini.
基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。
基于 LangGraph 和 DeepAgents 框架的智能体 Skills 能力演示项目。
基于 GJB 438C-2021 [5.10] 标准模板的 SRS 文档自动生成
Generate and review MiniMax H3 video prompts from user goals and multimodal references.
面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑，覆盖内容创作、设计视觉、工具集成、合规文书等场景。
Command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT LLM, SGLang and vLLM.
Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.
A git custom command that enhances Git's native worktree functionality with interactive features, automation, and repository migration capabilities.
先归根，再分化；先明道，再造物。 从混沌需求出发，生成可运行、可验证、可进化的 Agent Skill。
"Writing doesn't just communicate ideas; it generates them."