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 terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects to 1000+ app tools and MCP servers.
MCP servers for 200M+ patents, pharma records, scientific literature, and RD intelligence, powered by Patsnap's proprietary databases.
mTarsier - The Open Source MCP & Skill Manager for Claude, Cursor, VS Code & any AI client.
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。
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.
A股 AI 金融智能决策中台 · 129 个 MCP 工具 · eltdx 通达信协议 + akshare + 同花顺 + 东财 + 本地数据 · SmartRouter 多源降级路由 · 免费零鉴权
This is a PoC MCP server developed as part of some internal experiments during the development of CS 4.12 and the CS REST API. More information can be found here.
Ontology-based MCP server that analyzes database schemas (PostgreSQL, Snowflake, ClickHouse, Dremio) and generates RDF/OWL ontologies with SQL mappings for fan-trap-free Text-to-SQL.
An MCP server implementation that integrates the Hyperliquid SDK.
A memory, docs, and repo context layer for engineering agents.
Agent Skills
Open-source SEO, GEO, and marketing skills for AI agents.
Source control for agents. Use multiple coding agents, track their changes and query them in one place
Brigade — Your personal intelligence, built enterprise-grade
小黄（有温度）统一 Skill：品牌 IP 延展、中文轻手绘 PPT、文章封面与正文配图；先规划，再生成可交付 PNG。
An agentic skills framework
Prove your agent skills work before you ship them.
Agent orchestration for GitHub or Linear
AI-powered bug bounty hunting toolkit that works with or without subscription.
A new version of a ballistic calculator API, a new generation light-weight, LGPL library of modelling projectile trajectory in atmosphere
专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。
把一句视频需求、一篇实操文章、一个产品介绍，变成可执行的视频生产流程：先问清楚目标和风格，再拆脚本和分镜，再生成视觉预演 prompt，最后用 HyperFrames / Remotion / HTML / React 这类代码驱动方式生成可渲染的视频场景。
Tapestry - 基于 Agent Skill Bundle 的轻量级书签知识库