Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

A local-first MCP server that gives AI agents shared, durable memory through hybrid semantic search, SQLite FTS5, and a knowledge graph—without Docker or a required cloud service.

MCP server that lets Claude Code pause mid-task and ask a human a question via Slack — then resume once you reply.

Agent-operated App Store and monetization ops: metadata, IAPs, subscriptions, RevenueCat, paywalls, ASO, and analytics

An MCP server for your API

Official Huawei Cloud plugin for AI agents — skills, MCP tools, safety guardrails, and cloud sandbox to help AI agents build, deploy, and operate on Huawei Cloud securely.

1. Topics with new posts 2. Most active topics (past year/month/week/day) 3. Recently popular topics 4. Latest classified topics 5. Recently created topics 6.

A Claude Code plugin that turns Remotion from a motion graphics tool into a .

ScholarMCP - An academic research MCP server with comprehensive literature search, PDF ingestion, and citation management tools.

A monorepo of Unraid tooling: two MCP servers (Python and Rust) and three Unraid OS plugins, plus the Claude/Codex agent integrations that surface them.

Security AI helper for Caido: pipes your local Claude Code / Gemini / Codex / Copilot CLI through 18 MCP tools for manual web security testing. Local-first, no API keys.

MCP server that enables LLM agents to talk with IFC (Industry Foundation Classes) files

OpenMessage is a local-first messaging workspace for Google Messages, WhatsApp, and Signal. Use it from the native macOS app, the localhost web UI, or any MCP-compatible client.
Agent Skills

Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.

A skill pack that turns your coding agent into a PlanetScale database reviewer and operator. Point it at an organization and it audits configuration, query behavior, open recommendations, and safety...

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.

Agentic memory in a single SQLite file. Stop letting your agent re-read the same notes every session.

A repository for storing my dotfiles and AI config.

开发真正的应用很难。GSD、BMAD、Spec-Kit 等方法试图通过接管流程来帮忙。但在这么做的同时,它们剥夺了你的控制权,并且让流程中的 bug 极难排查。

Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers

A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth

Unofficial Python CLI for Google Flow. Drive Veo (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.

A skill library for people that make stuff

Smart memory for AI agents — Claude Code & OpenClaw

把前任蒸馏成 AI Skill,用ta的方式跟你说话。