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

Train in Silence The first Task-Aware MCP server for LLM fine-tuning. Stop comparing GPU prices. Start training. 中文

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。

Agent Browser eliminates the need to configure each MCP server in every client. Connect your clients once to Agent Browser, and it will manage all your Server-Sent Events (SSE) MCP servers for you.

A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client.

A Stdio MCP server which proxies an SSE MCP server.

MCP-based assistant for busy people who are context switching

is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.

A domain harness for AI-assisted mobile development and testing. Unified device logs, network traffic interception, and UI automation — exposed through APIs and MCP tools that let AI agents...

An MCP server that lets AI agents read and draw on the Figma canvas — safely. Paired with a Figma plugin, it provides structured verification, safe-by-default drawing, and resilient multi-window...

Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.

A progressive AI Agent Harness tutorial written in Rust.

Heimdall — MCP server for the Apple App Store Connect API and App Store Server API (StoreKit 2). 890 tools across 13 profiles, generated from Apple's OpenAPI spec, plus one-call macros for worldwide...
Agent Skills

Feishu Skills for OpenClaw 120+ 项飞书 API 实测经验,让你的 AI Agent 成为飞书自动化专家

🌐 LangSkills — Evidence-Backed Skills for AI Agents

Orchestrate Claude Code sessions as managed background processes from any OpenClaw channel.

Curated collection of Claude Code skills for intelligent project development with progressive loading and toolchain detection

A Claude skill for producing self-contained HTML artifacts instead of markdown when the task warrants it.

是为 Claude Code、Trae 等 AI 客户端设计的专业代码安全审计 Skill。采用白盒静态分析方法论,通过五阶段标准化审计协议,系统性发现和验证源代码中的安全漏洞。

Claude Code / OpenClaw Skill。装进 agent 后,用一句自然语言生成 9:16 竖版卡片组(图文)或短视频脚本,配 caption + hashtags,按规范落盘。支持真实素材图生图、卖点分析、5种标题公式。

A Claude Code skill that scans Solidity codebases for security vulnerabilities by referencing 36 unique vulnerability types sourced from smart-contract-vulnerabilities.

把任何 JSONL 格式的 RAG 源文件,轉換為結構完整、可驗證、可分享的 Claude Code Skill。

Скилл для AI-агентов: Claude Code, Codex, OpenClaw, Hermes и любых других, читающих SKILL.md. Берёт русский текст после нейросети и убирает всё, по чему его палят: канцелярит, «не просто X, а Y»,...

OpenClaw Skill — 微信 AI 个人助手 自动从微信聊天中提取待办、日程、干货,推送到 Discord,闭环追踪任务状态。 念念不忘,必有回响 — Important messages always echo back.

- Hierarchical architecture with intelligent orchestration