Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
An MCP server that provides access to LLMs using the LlamaIndexTS library.
AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems.
The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.
Secrets management for AI agents via MCP • @janeesecure
AI agents create, edit, layer, animate, and export SVG files using Inkscape. Works as an MCP server (stdio/HTTP), Claude Desktop .mcpb bundle, webapp dashboard, or Windows desktop app.
MCP server to enable an LLM to do basic static triage of a PE.
pixiv-cli brings the Pixiv ecosystem to the terminal: discover works and creators, manage accounts and collections, follow artists, bookmark artworks, and download visual works.
The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
SOMCP 是一个运行在 Android 手机上的本地 SO 逆向 MCP 服务器。它通过 Streamable HTTP 暴露 MCP 工具，让客户端可以在手机上完成 ELF 结构分析、Rizin 反汇编/分析、LIEF ELF 修复/重写、补丁会话、构建导出、Cloudflare Tunnel 暴露和可选 APK MCP 桥接。
This is an MCP server that connects Reaper projects to an MCP client like Claude Desktop, enabling you to ask questions about your projects and get comprehensive audio analysis for mixing feedback.
This package provides a powerful MCP server to equip LLMs with web access, going beyond naive methods of searching, fetching and extracting content.
Agent Skills
Herdr Browser renders a real Chromium view inside a Herdr pane and exposes it to Chrome DevTools Protocol clients.
AI Skill tra cứu thuế TNCN, SOP kê khai/quyết toán, hướng dẫn theo nhóm đối tượng.
This skill makes an AI agent write in a plain style. The full rules are in SKILL.md.
— 基于 Claude Code Agent Teams 的多智能体协作安全分析框架
面向电商商品图生产场景的图片套图 Skill。仓库提供一套从商品图分析、卖点提炼、Prompt 组织到成图输出的脚本与配置，适合用在淘宝、京东、拼多多、抖音等国内平台，以及独立站、Amazon 等跨境场景。
An agent-oriented skill for turning an SVG into a hand-drawn animation deliverable.
— 使用、修改或部署本專案，必須標明原作者 、附上本 repo 連結，並以相同授權公開原始碼。網路服務部署亦同。 本專案於 2026/04/13 從 MIT 切換至 AGPL-3.0。此日期之前取得的版本仍適用 MIT 授權。
一个封装了产品经理核心思维的 skill，帮助非产品经理用户写出高质量的产品需求文档（PRD）。 A skill that encodes core product management thinking to help non-PM users write high-quality Product Requirement Documents.
humble A humble, and fast, security-oriented HTTP headers analyzer
LLM Wiki 是一种用 LLM 构建个人知识库的方法论。与传统 RAG（每次查询从头检索）不同，LLM 会**，知识随每次导入和查询不断积累，形成复利效应。
ATR (Agent Threat Rules) is an open detection rule format for AI agent security threats. Rules are written as YAML documents conforming to a versioned schema, identified by the public ATR-YYYY-NNNNN...
Turn any LLM into a deterministic World Cup prediction engine with one prompt.