Cursor Install Guide
AI code editor frequently used with developer-focused MCP servers.
MCP Servers
Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP tools for codegen, browser control, and recordings.
douyin-mcp 让 AI 同时读懂你的抖音创作数据和视频内容 本地运行 · 音轨文案按需提取 · 数据可追溯 · 面向个人创作者的 MCP Server
MCP Server for Ozon marketplace - search products, get details, prices and delivery info
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
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.
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.
Sovereign, encrypted, portable memory for AI agents.
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
Please see the updated mcpb format Claude Desktop Extension
A mcp server that bridges Dune Analytics data to AI agents.
- 🧾 — every MCP tools/call request is now recorded in a dedicated, self-hosted table (wp_wsp_mcp_audit_log): tool name, timestamp (UTC), acting user (or unauthenticated), request IP, and the outcome...
Agent Skills
Every life is an odyssey. Find your next step in stories already lived.
Composable Google Sheets CLI for humans and agents. Read, write, update cells by key—with Agent Skills for Claude Code and OpenAI Codex.
A local tool for scanning open source repositories for security vulnerabilities and managing the disclosure process.
Você descreve a feature, o agente de IA especifica, planeja, executa em paralelo e que fez — com auditoria mecânica, não com promessa. Se a spec e o código desalinham, a máquina acusa.
通过 Codex + KSS MCP，用自然语言完成 TikTok Shop 商品运营、公开账号增长研究、内容驱动的私域获客和 TikTok 付费广告运营，并把可追溯的数据证据转成行动方案。
19 套可直接生图的视觉风格 Skills，为 gpt-image-2 编写。把文章、主题、产品或已有视觉资产编译成完整提示词。/ 19 visual-style prompt skills for gpt-image-2.
AI-agent skill for scoping, structuring, drafting, and reviewing empirical theses and dissertations
This repository hosts Agent Skills to run computational-chemistry tasks. These skills can be installed and used in OpenClaw, enabling OpenClaw to run complex computational-chemistry workflows.
A lightweight, debugger for the Android runtime (Dalvik/ART). avmdbg speaks JDWP over adb forward — pure Python, zero dependencies, cross-platform.
Build a persistent knowledge operating system with Obsidian provenance, scheduled loops, bounded static dependency graphs, context management, and multi-agent orchestration.
Validate Claude Code skills against the agentskills specification (Free tier)
that turn a brand brief into a complete visual identity — logo direction, brand-system board, mascot marks, and scenario colorways.