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
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
makes it easy to deploy and serve Haystack Pipelines and Agents.
(pronounced arc one [ɑːrk wʌn]) — Enterprise-ready MCP server for SAP ABAP systems. Secure by default, deployable to BTP or on-premise, and hardened with large unit/integration/E2E test coverage.
Deploy anything on your own servers. Connect a server, click deploy, done. MIT licensed and free to self-host forever.
Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.
Hosted uptime monitoring and public status pages for teams. Multi-region checks, automatic incidents, on-call alerts (Slack/Telegram/webhook/+), subscribers, REST API, Terraform provider, MCP server.
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.
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.
Find local coding-agent sessions and copy their user and assistant messages into another agent's native format. TUI, CLI and MCP.
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP tools for codegen, browser control, and recordings.
GCO is a platform that spins up EKS Auto Mode clusters across AWS regions, wired together with Global Accelerator for low-latency routing.
Agent Skills
Your agent invents things because it has no memory, and can't touch your database because it has no arms.
51 specialist AI agents for US healthcare administration. Installable prompts and skills for Claude Code, Codex, OpenCode, Cursor, Copilot, and other agentic coding tools.
A reasoning-first cinematic web design skill. Makes AI think like a film director — research a real film, extract its visual language, translate it into page narrative and composition.
Agent Skill for exploring Obsidian vaults with Enzyme — self-contained, cross-agent compatible
A multi-agent KiCad PCB design workspace: 9 skills driving a Phase 0-5 pipeline from topology discussion to Gerber shipout. Noncommercial.
Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code
勇哥餐饮.skill — 用勇哥（梁朝勇）方法论武装的餐饮创业决策 Agent Skill。含完整语料库、30+ 案例、保本线计算器、快招识别器、街景 360° 打分模型。
adds freshness decay (time-weighted memory), claim verification (verify_file_path MCP tool), 12 MCP tools (was 8), and 30+ bug fixes.
100个精心策划的AI驱动自动化循环，覆盖软件开发、数据科学、内容创作、产品运营、学习管理等多个领域。面向中国用户优化，全中文文档与提示词支持。
Make Codex pick the right skill or plugin more often.
Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.
Please see https://fast-agent.ai for latest documentation.