Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Secure MCP Gateway - Setup Admin level gateway functionality for MCP servers - with guardrails at each MCP server to overcome multiple security issues with using MCPs
An MCP server that provides tools for sending and testing in sandbox via Mailtrap.
Arthas MCP Server is an MCP-based diagnostic toolkit for Java applications, designed for LLM integration. It integrates with Alibaba Arthas so AI assistants can analyze and diagnose Java apps.
Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.
Lets Claude (and other AI assistants) talk to your photo catalog. Search photos, set ratings, edit develop settings, manage collections, import/export — all by chatting.
mcp server to run scripts on adobe illustrator
OCTAVE protocol - structured AI communication with 3-20x token reduction. MCP server with lenient-to-canonical pipeline and schema validation.
An MCP server bridging a high-capability model (Claude / GPT) to the firefox-reverse browser's built-in reverse-engineering engine.
WordPress block-level CRUD MCP server — path-based mutations, safety guards, preference scoring
支持ida headless 多文件分析
MCP server that teaches AI models to generate interactive visualizations — charts, diagrams, mockups, and more.
1. 下载右侧Release版本中7z文件并进行解压 2. VSCode插件库中搜索codex，安装Codex – OpenAI’s coding agent插件 3. 打开codex插件面板，点击右上角设置图标->MCP设置->打开config.toml 4. 添加如下配置
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."