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

Go server implementing Model Context Protocol (MCP) for filesystem operations.

Making docling agentic through MCP

(Repo: ruvnet/metaharness · CLI: metaharness · Library: @ruvnet/agent-harness-generator)

MCP-SecurityTools 是一个专注于收录和更新网络安全领域 MCP 的开源项目,旨在汇总、整理和优化各类与 MCP 相关的安全工具、技术及实战经验。

搜索 Notion 页面、查询数据库,并获取工作区知识。

- - 八字、六爻、紫微斗数、奇门遁甲、大六壬、梅花易数、塔罗、MBTI、面相、手相、合盘、周公解梦 - - 支持导出命理体系文本进行AI分析,多模型支持,深度推理,视觉识别 - - 支持 Model Context Protocol(MCP),可在支持MCP的agent中直接调用命理工具 - - 支持存储所有命理体系的记录,可将命理体系纳入个人知识库,显式引用命理体系数据源 - -...

A flexible Python library and CLI tool for interacting with Model Context Protocol (MCP) servers using any LLM model.

Install → your agent gets $10,000 paper money → trades real Polymarket order books → tracks P&L → competes on a public leaderboard. Zero risk. Real prices.

A solution for , allowing remote access and centralized management of model contexts.

BloodHound-MCP is a powerful integration that brings the capabilities of Model Context Procotol (MCP) Server to BloodHound, the industry-standard tool for Active Directory security analysis.

A simple implementation of an MCP server for using dify. It achieves the invocation of the Dify workflow by calling the tools of MCP.

🤖
Agent Skills

A curated AI Agent learning roadmap for people who want to build useful, reliable agents instead of collecting random links.

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.

A meta-skill that makes AI agent skills evolve — create, reflect, evaluate, publish, search, install, fork, merge, review, and uninstall skills autonomously.

Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity

Codex skill and standalone scripts for turning YouTube or local foreign-language videos into:

它不只帮你写“电影感、浅景深、光影高级”。 它会先设计镜头是谁,从哪里出发,按什么顺序经过哪些人,怎么绕过障碍物,最后停在哪里。

把投资人 的"供应链卡点逆向"投资逻辑和方法论操作化的** —— 不是模仿他说话,而是用他**的方式,帮你分析一只票 / 一个板块 / 一个 thesis。

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

A Codex skill that analyzes a real still image, decides whether it should use motion, micro-motion, or remain static, and writes a restrained image-to-video prompt without breaking typography, paper...

Shopify skills for agent collaboration

106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents.

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates.