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
ApocData · AI-native financial database for China A-share market. Drop-in Skill / MCP for Claude,ChatGPT, Qwen, Kimi, DeepSeek agents.
Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time.
MCP servers for 200M+ patents, pharma records, scientific literature, and RD intelligence, powered by Patsnap's proprietary databases.
Open-source infrastructure for AI agents — each gets an email address, folder, inbox, and API key. Move files through named inboxes instead of shared cloud credentials; signed receipts and MCP built...
Skarn plugins for Claude Code, Codex CLI, Gemini CLI, Grok Build, and Antigravity: audit skills, guard hooks, and MCP declarations that find leaked secrets and credentials in AI coding sessions,...
MCP Server 是实现模型上下文协议（MCP）的服务器，旨在为 AI 模型提供一个标准化接口，连接外部数据源和工具，例如文件系统、数据库或 API。
Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.
The most comprehensive Proton Mail MCP server ever created.
Let AI assistants read, search, and post in your Mattermost workspace
Send requests to OpenAI, Anthropic, and OpenAI-compatible providers using MCP protocol via tool or predefined prompts.
🌉 Local-first Proton Mail MCP and CLI through Proton Bridge. Search, read, draft, send, sync, and act on mail from Claude Desktop or Terminal.
Agent Skills
Refusal handling skill for vulnerability research evals
AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results
Harness for humans with ADHD
A single-file CLI to inspect and manipulate .env files, designed to be safe by default: values that look like secrets are in all output unless you explicitly ask otherwise.
Six Claude Code skills that harden Opus 4.8 toward frontier behavior — written by Fable 5, pressure-tested on the target model with transcripts included.
McKinsey-grade market research decks for Claude Code — adversarially verified numbers, 15 McKinsey methodologies as executable workflow, multi-agent pipeline. 一条指令产出敢被挑战的麦肯锡级市场研究 deck。
独立开发者信号雷达 Dashboard — 每天自动采集 19 个国内外信息源（App Store 新应用/GitHub 热榜/即刻圈子/36氪等），可视化浏览 + 收藏单条信息 + 中文翻译
A CLI for iKuai routers — manage network, users, VPN, firewall and more from the terminal.
Build multi-agent applications from YAML. Operate them from an evidence-aware terminal Studio.
Premium SwiftUI animation and interaction skills for AI coding agents — generate production-ready micro-interactions from plain English prompts.
Claude Code version of skill-autoimprove — auto-improve any CLAUDE.md using Karpathy autoresearch loop
A Claude Code skill plus guard hooks that give a non-frontier model Fable-5-grade work discipline: plan-gate, self-verification, and sub-agent routing, enforced mechanically.