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
Use Zotero, Obsidian, and NotebookLM together, or start with any two. research-hub gives your AI assistant a real CLI, MCP server, REST API, and dashboard for repeatable literature workflows.
An MCP server that connects AI assistants to your YNAB budget. Ask your budget questions YNAB can't answer.
An MCP server for AI agents to automate token swaps on Uniswap DEX across multiple blockchains.
- Search, compose, organize, and batch forward emails with natural language commands.
An MCP server for converting Markdown documents to PDF files. This server provides a simple and efficient way to generate PDFs from Markdown content with support for syntax highlighting, custom...
基于 MCP 协议的腾讯云 COS MCP Server，无需编码即可让大模型快速接入腾讯云存储 (COS) 和数据万象 (CI) 能力。
MSSQL MCP Server, provides database interaction and business intelligence capabilities. This server enables running SQL queries, analyzing business data, and automatically generating business insight...
mcp-name: io.github.n24q02m/better-email-mcp
Midnight has standardised on two official tools: - (docs Q&A / search): claude mcp add --transport http midnight https://midnight.mcp.kapa.
An MCP server providing 75 semantic analysis tools for Java, built directly on Eclipse JDT for compiler-accurate code understanding.
MCP Server for monday.com, enabling MCP clients to interact with Monday.com boards, items, updates, and documents.
Generate high-quality images from text prompts using Google's Gemini model through the MCP protocol.
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."