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

Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.

A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.

MCP-based assistant for busy people who are context switching

MCP server for interacting with Roblox game clients

This MCP server provides tools for listing and retrieving content from different knowledge bases.

Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

Spring AI Playground is a cross-platform desktop app for building, testing, validating, and executing MCP tools in a controlled local environment.

Open-source, local-first memory and context for AI agents. One memory store, every agent.

makes it easy to deploy and serve Haystack Pipelines and Agents.

开源金融数据 MCP / HTTP 服务,面向 AI Agent、量化脚本和普通后端集成。

make your ai track the progress of your project without drifting off

(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.
Agent Skills

你可以去全宇宙的任意地方完成“摄影”,并保持高质量的摄影风味

Skills and tools for scientific research with LLM agents. 给 Agent(如 Claude Code、Openclaw)提供的科研 skills

A Python framework for modular, self-contained skill management for machines.

Trending Claude Code skills

질문, 텍스트, 링크, 문서, 이미지, 데이터, 저장소를 출발점으로 삼습니다. 지원되는 입력과 실제 자료 접근은 사용하는 호스트의 기능에 따릅니다.

Stratawright is an agentic DAW that your AI agent (Claude Code, Cursor, Codex) can natively control so you can focus purely on making music.

Thirteen Claude skills that run an Instagram account: Reels off 26 scored hook formulas, a viral research skill, a caption linter, and a humanizer. Free, MIT.

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

Local-first Behavior CI for coding agents

A hybrid AI-powered security auditing tool for scanning skill directories and generating visual security dashboards.

A non-official Python toolkit for managing historical market data from data.binance.vision — designed from the ground up for AI agents and quantitative workflows.

Agent skills for working with DataHub — plan and review connectors, search the catalog, enrich metadata, trace lineage, manage data quality, and set up connections.