Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
An MCP server for Basecamp 3. It lets MCP-capable clients such as Codex, Cursor, and Claude Desktop read and manage Basecamp projects through OAuth-authenticated Basecamp API calls.
The local-first knowledge layer for AI development.
An MCP server that provides real-time data and insights from the Hyperliquid perp DEX for use in bots, dashboards, and analytics.
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。
Open-source SAST engine that traces vulnerabilities across files and functions
- — MCP Protocol v2 (spec revision 2026-07-28, streamable HTTP) and experimental StrongDM API support are here — see the release notes.
MCP server for interacting with Apache Superset, enabling AI agents to connect to and control a Superset instance programmatically.
Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work).
Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.
The cognitive memory layer for AI agents.
Local multi-agent coding orchestrator with 22 pipeline roles, TDD enforcement, SonarQube integration, and automated code review. Supports Claude, Codex, Gemini, OpenCode and Aider.
A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.
Agent Skills
Install complete Claude Code infrastructure in 30 seconds with automatic framework detection and skill auto-activation.
OmniBox-Spider-Skills 是一个面向 OmniBox 爬虫开发的技能仓库，提供可复用的技能说明、规则约束与结构化参考文档，帮助开发者更快完成爬虫源的编写、调试、回归检查与持续维护。
Skill to generate the knowledge vault for projects using the Ralph loop
🌐 LangSkills — Evidence-Backed Skills for AI Agents
Orchestrate Claude Code sessions as managed background processes from any OpenClaw channel.
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。
A Claude Code skill that scans Solidity codebases for security vulnerabilities by referencing 36 unique vulnerability types sourced from smart-contract-vulnerabilities.
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.
Expert automation skills for Claude Code, organized by department.
OpenClaw skills that replace a human executive assistant.