Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Citra — PDF answers with page-level proof. Local-first structured text, tables, OCR, visual evidence, and citations via MCP, CLI, and SDK.
CodeGraph transforms your entire codebase into a semantically searchable knowledge graph that AI agents can actually reason about—not just grep through.
Token-efficient MCP adapter for Pi coding agent
一个将ACE(Augment Context Engine) 做成MCP的项目
LLDB MCP Integration + other helpful commands
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client.
🧠 Self-Reflecting AI Queries → MCP Protocol Integration → Intelligent Vulnerability Scanning
Autonomous bug-bounty framework for Claude Code and 6 other AI coding tools — 50 agents, 26 commands, 19 CLI tools, 11 skills, 2 MCP servers.
Headless IDA Pro MCP Server
Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.
An MCP server for interacting with Sentry via LLMs.
Claude spawning scene objects and controlling their transformations and materials, generating blueprints, functions, variables, adding components, running python scripts etc.
Agent Skills
Spider King 是一套面向 Web 协议恢复、参数还原、挑战链路拆解与纯协议交付的逆向工程 Skill。
A Claude Code Skill that transforms any idea into professional Seedance 2.0 video storyboard prompts.
Multi-platform AI skill pack for generating, reviewing, and refactoring web UI with stronger visual judgment.
LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window.
Production-ready patterns for React Native development, packaged as a Claude Code plugin. Maintained by Software Mansion.
LightClaw: The Real Lightweight AI Assistant
managed-agents helps teams move AI agents from demos to production with runtime infrastructure for sessions, tools, approvals, sandboxed execution, memory, credential vaults, audit trails, replayable...
This collection of skills grew out of my day-to-day paper-writing workflow and has been iteratively refined over time.
⚠️ 本项目是作者为**而创建的个人学习项目，代码结构和实现均以探索为目的，。 ：网页版 AI 对工具调用的支持参差不齐，稳定性和准确性均有较大局限，距离实用仍有差距。 OpenLink 通过浏览器扩展模拟用户操作来驱动网页 AI，，不适合作为日常 API 调用使用。请合理使用，勿滥用。
An analysis of Moonshot AI's Kimi agent architecture (K2.5 model).
A simple template for creating persistent AI companions that remember you
A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).