Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
Package bug screenshots into AI-ready fix instructions with MCP Server
Wot UI 的 AI 能力工具集：Skills、MCP 协议与 CLI 工具等
Lightweight MCP server for Ghidra-based reverse engineering with iOS, Linux, and game file support
MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.
Solidity static analyzer you can talk to. MCP integration for Claude Code, Cursor, and Windsurf.
Minimal MCP server for calling any KIE.ai endpoint. Pure HTTP shim — no model registry; agent constructs payloads from docs.kie.ai.
Burp MCP proxy with compression pipeline — reduces 182KB responses to ~4KB
Control your Apple HomeKit smart home from AI assistants, the terminal, and automation tools.
Infinite text-free AI image generator + SQLite-indexed multilingual vault & gallery — with a local MCP your AI can drive.
AI agents control Figma through code execution.
Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.
arcticdb-mcp An MCP server for structured read/write access to ArcticDB. Overview • Demo • Quick Start • Configuration • Tools • Development
Agent Skills
Universal memory layer for AI Agents
🔬 Harness Vibe Research with Self-evolving AI Scientists
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
![Build status][build-url] ![Coverage status][coverage-url]
A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.
Scans your project, detects your tech stack, and installs curated AI agent skills automatically.
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
(刺し子, literally "little stabs") is a form of decorative reinforcement stitching from Japan. Originally used to reinforce points of wear or to repair worn places or tears with patches, here it...
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
A collection of interesting libraries and tools for Avalonia project.
Xiaomi Miloco
Type one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps building, testing and fixing until it is...