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 VS Code compatible extension (Cursor, Windsurf, Antigravity etc.) that allows Stata code to be run directly from the editor. Enables AI agents to directly interact with Stata.
Descript MCP plugin for Cursor, Claude Code, and Antigravity — edit video and audio by editing text, from your agent
Live SEO + AI Search (AEO) dashboard template powered by the Graphed MCP. Hand to a coding agent, point at your workspace.
Magic UI components, searchable and installable from your AI editor.
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
PostgreSQL schema intelligence MCP server with offline linting, migration safety, query validation for AI coding assistants.
Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.
parallel-browser-mcp is an MCP server for parallel browser automation. It exposes a numeric session model over MCP so one client can create and control multiple browser sessions at the same time...
Talk to Claude, Cursor, Windsurf, Cline, or any MCP client in plain English and it sets breakpoints, reads memory, disassembles, traces, dumps PEs, and bypasses anti-debug — live, inside the debugger.
Static analysis that finds the mess vibe coding leaves behind — dead code, duplicated logic, scaffolding artifacts, and disconnected functions — across 16 languages.
MCP Server for Contrast Security
Agent Skills
see README.en.md for the full English version.
Your AI watches your workflows and turns them into reusable Hermes skills — automatically.
Fusion-Fable is a Claude Code skill that runs a hard question through a pipeline. The same prompt is dispatched to several models in parallel — each answering independently with web search and bash,...
Empirically detect the repetitive defaults a model falls back on, then turn those findings into a reusable instruction file that makes future outputs less generic.
这份 Skill 的目标很明确：中文技术写作应更克制、更准确、更易读。不追求宣传感，也不试图把所有内容都写成统一模板，而是聚焦几类高频问题：
Desktop AI assistant powered by Claude API
A collection of Claude Code skills for academic research review. This tool was developed by Claes Bäckman.
Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.
Official skills for the GLM family of models, designed for agent architectures including Claude Code, OpenCode, OpenClaw, AutoClaw, and other AI coding agents.
⛏️ Turning data into a visual language for better thinking with Skills.
WeChat chat history analyzer — runs in Claude Code, generates dual-user visualization + AI personality comparison report. No API key needed.
Tools for empirical economics research with Claude Code — audit protocols, presentation systems, PDF workflows, and a research GTD harness.