Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers

A Model Context Protocol (MCP) server that provides access to the DBLP computer science bibliography database for Large Language Models (accompanying paper accepted to AI4SC @ AAAI-26).

A complete, robust Model Context Protocol (MCP) server for Microsoft OneNote integration with Claude Desktop. Access your entire OneNote knowledge base through natural language queries.

A Node.js application that connects WhatsApp Web with AI models through the Model Context Protocol (MCP).

A tool that creates MCP (Model Context Protocol) servers from OpenAPI/Swagger specifications, enabling AI assistants to interact with your APIs. for specific APIs or services.

Search, read, organize, reply to, and send email through supported password- or app-password-based IMAP/SMTP accounts—from Claude, Cursor, Codex, and other MCP clients.

A Model Context Protocol (MCP) server that provides comprehensive stock screening and fundamental analysis capabilities using Finviz data.

An MCP (Model Context Protocol) server that enables AI platforms to interact with YepCode's infrastructure.

A Model Context Protocol server that connects to Bluesky and provides tools to interact with the ATProtocol.

基于 MCP (Model Context Protocol) 协议构建的 A 股金融数据 AI 助手扩展 (v0.1.0)

An MCP (Model Context Protocol) server for Cronometer nutrition tracking, built on the reverse-engineered mobile REST API.

A Model Context Protocol (MCP) server for interacting with Astra DB. MCP extends the capabilities of Large Language Models (LLMs) by allowing them to interact with external systems as agents.

OpenCTI MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with OpenCTI (Open Cyber Threat Intelligence) platform.
Agent Skills

iOS and watchOS SwiftUI sample code demonstrating a variety of good and bad accessibility techniques. Learn how to apply WCAG 2.2 to iOS SwiftUI apps.

I built an OpenClaw agent that manages Google Ads accounts through intent analysis instead of bid automation. All three layers — Read → Draft → Apply — are live and tested on real accounts.

https://github.com/user-attachments/assets/e3ed5b34-1ddb-43a6-af42-2d1a907d3564

This repo was the testing ground for building the Claude Code ecosystem below. The skills here have been consolidated into svelte-skills-kit which is actively maintained.

A two-pass pipeline for removing the signs of AI writing from outward-facing text, packaged as Claude Code Skills.

A community collection of skills for Minis — reusable instruction sets that extend Claude's capabilities with specialized workflows, domain knowledge, and bundled resources.

is a framework for long-term life simulation in multi-agent societies. Agentopia simulates human social life across years: In our experiments, 100 agents autonomously take part in social life over 10...

A Meta-Skill for Private-First Distribution of Agentics (Skills, Agents, and Prompts) across your Agents, Devices, and Teams.

managed-agents helps teams move AI agents from demos to production with runtime infrastructure for sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, replayable...

Personal skill collection for , , and — by @LichAmnesia.

1인 사업가 생산성 키트 — 직원 없이 49개를 자동화했고, 그중 바로 쓸 수 있는 AI 에이전트 스킬 26개(+실행 스크립트)를 공개합니다

我自己在用的 Claude Code Skill 合集。 一次 clone,装好里面全部 skill。