Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
Drop‑in Express middleware and helpers to add secure auth to your Model Context Protocol (MCP) server with Descope. Ship an authenticated /mcp endpoint and register tools in minutes.
Conduct iterative, deep research using Google Gemini 2.5 Flash with Google Search Grounding and URL context. No web-scraping dependency is required.
This repo contains MCP tools and sample agents for fetching public information from Data Commons.
Minimal, spec-faithful Python framework for building Model Context Protocol (MCP) clients and servers.
A self-hosted error tracking engine for Rails 8+ applications. Track errors, get notified, and resolve issues—all without external services.
AI intelligence flows as streams — tokens, tool calls, memory, voice, documents. NeuroLink is the vascular layer that carries these streams from where they are generated (LLM providers: the neurons)...
Run any dockerized MCP Server in a sandboxed container and connect to it remotely
is a semantic testing framework for .NET — write AI tests in , run them with .
Process documents 100x larger than your LLM's context window—without vector databases or chunking heuristics.
Muppet is an open-source toolkit designed to simplify the entire lifecycle of your Model Context Protocol (MCP) servers—from development and testing to deployment.
As AI systems become increasingly integrated into software supply chains, enterprise applications, and security infrastructure, the need for structured, secure, and interpretable model interaction...
一个高性能的文档转换服务器，同时支持 和 接口。将 PDF、Word 和 Excel 文档转换为 Markdown 格式，具备图片提取、页眉页脚移除和批量处理等高级功能。
Agent Skills
The MATLAB Agentic Toolkit brings trusted MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
- Extensibles Validation Plugins. - Sync & Async Validation (w/ Promises & automatic errors). - Nested Fields (w/ Serialization & Validation).
Screenshot testing is key to validate your app's appearance and functionality. It efficiently detects visual issues and tests the app as users would use it, making it easier to spot problems.
Large Language Models (LLMs) have rapidly evolved into powerful general-purpose reasoning and generation engines.
山音超级编剧大师 - 全格式影视编剧 Skill 由 @山音 设计的自然语言驱动编剧 Agent Skill 覆盖 1-3 分钟概念超短片→90 分钟电影长片→多集剧集的全流程剧本创作，一站式搞定人物、大纲、场景、剧本全链路
vet supports special mode for Agent Skills. Run vet scan --agent-skill to scan an Agent Skill hosted in a GitHub repository.
Visual skill manager for AI agents. Desktop app and TUI.
基于 Vant 设计语言，为小程序与 H5 提供一致、类型安全且高度可定制的开发体验。
简单说，就是跟 Claude 说一句话，它会帮我从每天的新论文里筛一轮，挑出值得看的，再把重点论文读完、写成 Obsidian 笔记。日常不用记一堆命令，基本就是：
· · · crafted on a 24×24 grid and trusted by 500,000+ developers.
NeMo Gym is a library for evaluating and improving models and agents using environments. NeMo Gym provides infrastructure to develop environments, scalably run evaluation and training, and a...
A collection of Codex/agent skills for planning, documentation access, frontend development, and browser automation.