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
A Model Context Protocol (MCP) server for querying the VirusTotal API. This server provides comprehensive security analysis tools with automatic relationship data fetching.
A Model Context Protocol (MCP) server that provides persistent context management for Claude AI coding assistants. Never lose context during compaction again!
Bridge between the amazing Super Productivity app and MCP (Model Context Protocol) servers for Claude Desktop integration.
A Model Context Protocol (MCP) server that enables AI assistants to interact with WordPress sites through the WordPress REST API.
Agent-facing Model Context Protocol server and skill for Langfuse observability.
opencode-mcp is an MCP server that bridges your AI tools (Claude, Cursor, Windsurf, VS Code, etc.) to OpenCode's headless API.
A Model Context Protocol (MCP) server for developing Django applications, inspired by Laravel Boost. This server exposes Django project information through MCP tools, enabling AI assistants to better...
The secure, lightweight open-source AI agent framework.
Guardrailed video editing MCP server for AI agents. Local-first FFmpeg tools, Video Receipts, quality gates, Hyperframes, and Shorts/Reels repurposing — for Claude Code, Cursor, and any MCP client.
AI-driven quality and governance MCP Server for dbt projects. Audit coverage, profile data, detect schema drift, and auto-generate documentation—all through natural language with an AI assistant.
Bring Claude Code–style sub-agents to any MCP-compatible tool.
Detect hardcoded secrets, shell injections, remote-code execution, over-privileged filesystems, and unpinned supply-chain risks across , , , and before they run.
Agent Skills
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects.
50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
A skill is a folder containing a SKILL.md file with instructions an agent loads on demand. Think of it as a reusable, portable prompt: when this scenario comes up, do these things.
A set of ready to use Agent Skills for building, testing, analyzing and publishing browser extensions.
Directly edit and manage Overleaf projects from Codex or a terminal. The bundled enhanced olcli sends small, verified remote changes instead of requiring a download-edit-upload cycle for the whole...
开源我自己做的一下好用的skills
An Extensible Agentic Markup Language
Claude Code skill for academic manuscript writing: IMRAD workflows, literature matrices, tables/figures, and tested utilities.
20亿Claude Opus 4.6-4.8的Token
面向全国大学生数学建模竞赛（CUMCM）的完整建模论文分步审核工作流技能，兼容 Codex、Claude Code 等支持 Agent Skills 规范的 Agent。
它扣掉的只有两件事：固定 IP 形象和固定配色。使用者只需要填写自己的 IP 角色公式和品牌配色，就可以把文章、知识点、教程内容转成一套带个人风格的配图 Prompt。
SEO Landing: Give your AI coding agent the capabilities of a senior Technical SEO engineer. An agent skill for building high-performance, technically optimized SEO landing pages.