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

is a lightweight, open-source Model Context Protocol server that bridges AI agents and the macOS operating system.

Create 3D models, add features, and automate CAD workflows using conversational AI.

Postgres MCP Pro provides configurable read/write access and performance analysis for you and your AI agents.

Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.

A Model Context Protocol (MCP) server that provides structured spec-driven development workflow tools for AI-assisted software development, featuring a real-time web dashboard and VSCode extension...

A Swift implementation of the MCP (Model Context Protocol) for JSON-RPC over various transports.

MCP server to provide Figma layout information to AI coding agents like Cursor

MCP server for Grafana

Production ready MCP server with real-time search, extract, map & crawl.

Monorepo providing 1) OpenAPI to MCP Tool generator 2) Exposing all of Twilio's API as MCP Tools

- gives AI assistants deep read/write access to the Unreal Editor through 24 category tools covering 736+ actions, plus a YAML flow engine for multi-step workflows.

MCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objective-C APIs & code examples in Claude, Cursor & AI assistants
Agent Skills

Turn Claude into a Senior Design Architect — DTCG design tokens, 42 components, WCAG 2.2 accessibility, any-framework code, 138 design systems, and runnable skills.

A terminal workbench in pure Rust: shells, persistent sessions, SSH, coding agents. GPU-rendered on Zed's gpui, VT core from Alacritty.

One command. 25 agent skills. Zero to profitable business.

Agent skills and a reference guide that teach AI coding assistants to write Rails the 37signals way — extracted from Fizzy, Campfire, and 100+ of DHH's code reviews.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

This repo may be replaced by nuxt-skill.onmax.me. Stay tuned.

Generate and evaluate agent skills based on traces with agents. Create skills with teacher models (expensive/slow) that student models (cheap/fast) can use to perform harder tasks reliably.

JSON spec -> .excalidraw + .png + animated .gif

Demo: Analyzing 2 years of NVDA, AMD & SPY stock data (15,000+ lines of raw JSON) using DeepSeek V3.2

Local FFmpeg · No cloud · No API keys · Python standard library Claude Code · Cursor · Codex · MCP

Thirteen curated Agent Skills package the steps, templates, scripts, examples, and quality gates behind repeatable work. They follow the open SKILL.

Agent Plugins is an open, vendor-neutral standard for packaging reusable components that extend AI agents into distributable plugins.