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
A domain harness for AI-assisted mobile development and testing. Unified device logs, network traffic interception, and UI automation — exposed through APIs and MCP tools that let AI agents...
You built an agent. Now you need to tune the prompt. Swap the model. Restrict access for specific users. Figure out what it's actually costing you.
is a local stdio MCP server that lets an Agent ask configured multimodal providers to inspect an explicitly supplied image, video, audio file, or music file.
Streamable HTTP MCP server for Claude.ai custom connectors.
Build your Plaid integration in record time with a development toolkit for your AI coding tools, including prompts, sandbox data, and an MCP server.
Local semantic code index and MCP server for Claude Code, Codex, and opencode. Includes semantic search, reuse checks, impact analysis, and a VS Code chat and agent supporting local CLIs and API...
Free, open-source sports-data MCP server — 841 tools across 64 providers: cross-book betting odds, official league stats, racing, fantasy, cricket, F1 and more. 44 providers need no key.
Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.
A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.
The open-source trust layer for bringing Claude Code (and other autonomous AI agents) to work — with your security team's approval.
Four small MCP tools that let apfel (Apple's on-device LLM) reach the web and read local files: url-fetch (read a page), ddg-search (web search), search-and-fetch (search+read in one call), fs...
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Agent Skills
civ-finish-quotes is a platform-neutral skill and toolkit for adding Civilization-style completion quotes to real finished work.
- 对话、工具调用、检索过程都会落到本地文件 - 长期记忆使用可直接编辑的 Markdown - 技能不是黑盒函数，而是可读可改的 SKILL.md - 前端可以直接看到流式回复、工具链路和检索证据
基于 Claude Code 的 AI 辅助中文网文创作系统，集成 7 个专业 Skills + 1 个 Agent，覆盖从拆书分析、大纲规划、逐章创作、去 AI 润色到成稿输出的完整工作流。
将 AutoKernel 的 6 层调优手册拆解为 （约 1,500 行），覆盖 7 个 LLM 核心算子 + NVIDIA/AMD 双平台。
A Claude skill for designing comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing).
Autonomous skill generator that enables AI agents to learn new technologies from the web. Use this skill when you want to research a library, framework, or tool and generate reusable...
Distills Linus Torvalds' code-review methodology from his LKML emails into a reusable, language-agnostic skill.
*Write projections easily with generation*.
This is the branch tracking v7 work. If you are looking for the published latest on npm check out v6 branch.
, verb. To stamp a mark that cannot be erased. noun. The mark itself, permanent, portable, unmistakably yours.
A small helper that tries to keep Engineers in step with the pace of Vibe Coding.
Turn a web page into records your agent can use, from one 3 MB binary.