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
MCP server: Project PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.
Gemini Vision & Image Generation MCP for Claude Desktop and Claude Code
Ever tried using Cursor or Claude to write Playwright tests? Yeah, it's kind of a mess.
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
MCP server for Google Gemini image generation with configurable model support.
MCP MySQL Server 是一个基于 @modelcontextprotocol/sdk 的 MySQL 工具服务，支持 SQL 查询、表结构获取、连接检测等功能，适用于 AI 代理、自动化工具等场景。
is a media-generation agent: generate images, video, and audio, transcribe, render HTML, search the web, run code, and chain multi-step media operations — from any MCP client.
MCP server for Fly.io CLI integration with Claude Desktop
I've been running this Gemini MCP server in my Claude Desktop setup for months. It's one of the few I leave on permanently — not because Gemini replaces Claude, but because grounded search, image...
The jMRI (jMunch Retrieval Interface) specification — an open interface standard for token-efficient context retrieval in MCP servers.
Review Analyzer — agent-native VOC for e-commerce. 6 MCP tools, ASIN or CSV input, black-gold dashboard. Backed by Shulex VOC OpenAPI (10 markets).
A standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP servers
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."