Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.
Sovereign, encrypted, portable memory for AI agents.
Your digital developer twin — because "explain our setup again" gets old fast.
A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
An MCP server that connects to a Swagger specification and helps an AI to build all the required models to generate a MCP server for that service.
A Stdio MCP server which proxies an SSE MCP server.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
MCP server to enable an LLM to do basic static triage of a PE.
MCP server to extract contents from a PDF file
Shared MCP server for the Upvote.club Public API.
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
Agent Skills
audit-prompt-caching is a portable Codex/agent skill for finding why LLM cache reuse fails across the request path: prompt/prefix caches, provider cache telemetry, cache-aware routing, agent tool...
Create hand-drawn Excalidraw diagrams from the command line. Generate .excalidraw files, manage diagram checkpoints, export to excalidraw.
An open-source, Persian-first desktop agent that can work in your files, understand your voice, and keep going from Telegram.
Turn one human UI page flow into reusable automation capabilities, then assemble new testing flows from those capabilities instead of recording everything again.
Reusable finance Agent Skills — grounded in LLMQuant Data
A collection of installable for AI coding agents, built to play together instead of sitting in a grab bag.
While other collections link to external repositories, provides a self-contained, ready-to-use library of complete skills. Every skill in this repository is a full SKILL.
Review reconstructed geometry and generated CAD documents before using this version in production.
A collection of skills for deploying and benchmarking vLLM. This project follows the anthropics/skills template format and is installable as a Claude Code plugin marketplace.
https://github.com/cv-cat/Spider_XHS 这个仓库用于存放基于 Spider_XHS 封装的 Agent Skills。
A curated set of practical skills and examples for building AI applications using Sarvam APIs.
skill-check validates agent skills with clear diagnostics, auto-fix support, quality scoring, and optional security scanning.