Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

A memory, docs, and repo context layer for engineering agents.

We use AI for everything - analysis, reports, strategy. But when it comes to actually seeing the story in your data, you're stuck copying numbers into a spreadsheet and building charts yourself.

— A crypto data gateway for AI assistants, powered by the BlockBeats Pro API.

Search and memory across your AI coding sessions — one index over Claude Code, Codex, and Pi. Fuzzy-find and resume from the CLI, give agents recall via MCP, and get usage reports.

Minimal but real MCP server that ingests a GLB/GLTF floorplan scan (for example captured with Polycam https://poly.cam/) and exposes deterministic spatial tools over a compact derived scene graph.

AI-native video editor driven as a local MCP server. Linux + Windows: ingest, transcribe, edit graph, melt/ffmpeg render, QC.

Grok Build plugin for Claude Code, Grok, Codex, Cursor and others. Provides /grok:search, /grok:review, /grok:rescue commands + grok_search MCP tool for live X/web search.

下载 AI-Browser-MCP-x64-v3.0.0.zip(~157MB),解压运行 AI-Fbowser-Mcp.exe。在 Cursor / Claude 里说句话,**自动执行:采集数据、逆向 POST 加密、CDP 定位签名算法、自动填表。

Universal Memory Protocol (UMP) - an open standard for agent memory. The third interop layer beside MCP (tools) and A2A (coordination).

一个 MCP Server 连接所有数据库,数据库 MCP Server 的瑞士军刀。

is a remote MCP service provided by Aqara Agent. It lets MCP-enabled AI applications securely connect to Aqara smart home capabilities.

A powerful CLI + MCP Server for working with photos: search, edit, tag and describe photos right from the terminal.
Agent Skills

两个配套的 Agent Skill:一个搭 harness,一个给 harness 体检。标准 SKILL.md 格式,Claude Code / Codex / Cursor / OpenClaw 通用,脚本也能直接当 CLI 跑。五层框架 + 可视化报告,破坏性动作一律先出方案等你点头。零依赖。

Jetpack Compose & Kotlin AI agent skills for Cursor, Claude Code, Codex, Gemini & 27+ agents. Strict MVI · Kotlin 2.x K2 · Compose 2026 · CI-validated.

Give Claude, Cursor and other AI agents access to your live website analytics and experiments — so they can find conversion problems, recommend tests, implement tracking and evaluate results.

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

대량 생성한 스킬 모음이 아닙니다. 개발동생이 매일 쓰는 워크플로에서 검증한 에이전트 스킬만 골라 담았고, Claude Code, Codex, Cursor에서 동일하게 동작합니다. 필요한 스킬만 개별적으로 설치할 수 있습니다.

A Claude Code skill that establishes a structured institutional knowledge system for your projects. Track bugs with solutions, architectural decisions (ADRs), key project facts, and work history in a...

25 skills for the parts of shipping that code review never covers: the loading states, the type scale, and whether half the diff is AI slop.

Less skills. Deeper connections. A lean, interconnected skill ecosystem for AI coding assistants. 67 skills · 248 connections · 46 signals · 13 platforms · MIT

SLV is a CLI tool that handles the full lifecycle of Solana infrastructure — from bare metal to running node. The built-in AI Console lets you deploy and operate nodes through natural conversation.

Portable agent skills for training, evaluating, and running inference on NVIDIA TAO models. Works with Claude Code, Codex, Gemini CLI, or any coding agent that speaks the Agent Skills open standard.

Lola is a universal AI Package Manager. If an agent's skills were an RPM, Lola is the DNF for it. Write your skills and context modules once as portable packages, then install them to any AI...

Agent skills that teach AI coding agents Feature-Sliced Design (FSD) v2.1 architectural methodology.