Cursor Install Guide
AI code editor frequently used with developer-focused MCP servers.
MCP Servers

This repo provides a reference implementation for creating a remote MCP server that supports the Streamable HTTP & SSE Transports, authorized with OAuth based on the MCP specification.

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.

furi is an easy to use, CLI & API for MCP management.

The cognitive memory layer for AI agents.

Desktop Extensions: One-click local MCP server installation in desktop apps

A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.

A canvas design tool your agent can edit. Arrange structured UI nodes on the canvas; connect Claude, Codex, Cursor, or opencode over MCP and it works on the same document.

Intercept AI requests, track usage, inject MCP tools centrally

Open security engineering for code written by humans and AI agents. Discover. Repair. Verify.

Battle-tested Odoo knowledge for AI agents, validated against real Odoo v17 instances in CI.

PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human

Desktop extension (.mcpb) for Claude Desktop. Single-click install via Settings → Extensions.
Agent Skills

🛡️ 网络安全 · 渗透测试 · 攻防对抗 · 红蓝对抗 · AI Agent Skills

This repository contains a JetBrains-filtered and JetBrains-verified snapshot of upstream GitHub agent skills collected into a flat local directory layout for easier discovery and reuse.

Hey friends. Shawn here. I've been bootstrapping and starting companies for the past 10 years (still working hard at 996 level).

A cross-platform desktop app for managing AI agent skills. Browse, install, sync, and edit skills across 16 agents from a single interface.

这是一个 ,让 AI 能够使用 IDA Pro 自动分析恶意软件,就像人类安全分析师一样:

这是一个专为 NSFC 申请书撰写设计的 Agent Skills 集合,帮助科研人员提高申请书质量,涵盖写作指导、图表制作、文献管理和政策速查等核心环节。

Agent skills for secure smart contract development with OpenZeppelin Contracts libraries.

JDArmy BREAK stands for — an open framework for enumerating and mitigating business risks. By systematically classifying, describing, and cataloguing a wide range of business risks, it provides a...

给 Claude Code、Codex、OpenClaw 等 Agent 使用的创作者公开内容研究 Skill。

Secured by SHA-pinned GitHub Actions · npm provenance · OIDC Trusted Publishing — see SECURITY.md .

SKILL 是一种模块化、自包含的扩展包,通过提供专业的领域知识、工作流程和工具来增强 AI 的能力。你可以将它们视为特定领域或任务的"入职指南"——它们将通用 AI 助手转变为具备程序化知识的专业助手。

A collection of AI agent for CPU performance analysis and optimization on x86 Linux. The skills give an agent structured, multi-step workflows for profiling with Linux perf, identifying performance...