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

A flexible Python library and CLI tool for interacting with Model Context Protocol (MCP) servers using any LLM model.

MCP-SecurityTools 是一个专注于收录和更新网络安全领域 MCP 的开源项目,旨在汇总、整理和优化各类与 MCP 相关的安全工具、技术及实战经验。

- - 八字、六爻、紫微斗数、奇门遁甲、大六壬、梅花易数、塔罗、MBTI、面相、手相、合盘、周公解梦 - - 支持导出命理体系文本进行AI分析,多模型支持,深度推理,视觉识别 - - 支持 Model Context Protocol(MCP),可在支持MCP的agent中直接调用命理工具 - - 支持存储所有命理体系的记录,可将命理体系纳入个人知识库,显式引用命理体系数据源 - -...

Search pages, query databases, and retrieve workspace knowledge from Notion.

(Repo: ruvnet/metaharness · CLI: metaharness · Library: @ruvnet/agent-harness-generator)

Install → your agent gets $10,000 paper money → trades real Polymarket order books → tracks P&L → competes on a public leaderboard. Zero risk. Real prices.

MCP for Proxmox integration in Cline

Repo of skills for autogen studio using model context protocol (mcp)

An intelligent research assistant powered by Perplexity's specialized AI models. Features automatic query complexity detection to route requests to the most appropriate model for optimal results.

A high-performance Rust implementation of a Model Context Protocol (MCP) server for headless terminal ht.

BloodHound-MCP is a powerful integration that brings the capabilities of Model Context Procotol (MCP) Server to BloodHound, the industry-standard tool for Active Directory security analysis.

This project demonstrates how to integrate the Model Context Protocol (MCP) with customized LLM (e.g. Qwen), creating a powerful chatbot that can interact with various tools through MCP servers.
Agent Skills

My Codex Skills

Before I go to bed, I tell my agents: good night, have fun

Distributable agent skills for Composio developers. This repository contains comprehensive guides and best practices for building AI agents with Composio's Tool Router and Triggers.

Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.

A collection of agent skills for pharmaceutical R&D.

Claude Code skills for the Harness.io CI/CD platform. Generate pipeline YAML, manage resources, debug failures, analyze costs, and more from natural language.

A curated list of OpenClaw-related products, skills, communities, and ecosystem resources — organized by use case.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.

Claude Code / Codex skill — 面向中国 AI / ML 研究者,主投 、次投 、必要时冲刺 的论文写作技能。

首先感谢 Andrej Karpathy 的《LLM Wiki》原文。这个项目直接受那篇 idea file 启发而来。

adds freshness decay (time-weighted memory), claim verification (verify_file_path MCP tool), 12 MCP tools (was 8), and 30+ bug fixes.

Curated guidance for AI assistants building MapLibre applications — covering ecosystem and open-source best practices.