Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
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
AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency.
A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).
Clip any video into a narration recap with claude code skill｜用 claude code skill 把任何视频剪辑成中文解说视频，支持剪映导出
A simple template for creating persistent AI companions that remember you
The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.
我自己在用的 Claude Code Skill 合集。 一次 clone，装好里面全部 skill。
139个完整的小红书运营技能 - Claude Code 技能插件系统。覆盖内容创作、账号运营、互动运营、数据分析、电商转化、平台规则、工具生态、营销推广、增长策略9大分类。
做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
An analysis of Moonshot AI's Kimi agent architecture (K2.5 model).
⚠️ 本项目是作者为**而创建的个人学习项目，代码结构和实现均以探索为目的，。 ：网页版 AI 对工具调用的支持参差不齐，稳定性和准确性均有较大局限，距离实用仍有差距。 OpenLink 通过浏览器扩展模拟用户操作来驱动网页 AI，，不适合作为日常 API 调用使用。请合理使用，勿滥用。
This collection of skills grew out of my day-to-day paper-writing workflow and has been iteratively refined over time.
managed-agents helps teams move AI agents from demos to production with runtime infrastructure for sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, replayable...