Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers

A type-safe implementation of the official Model Context Protocol (MCP) schema in Rust.

Provide AI MCP server args during runtime.

A simple Slack bot that uses the Model Context Protocol (MCP) to enhance its capabilities with external tools.

This is a starter template for creating your own Model Context Protocol (MCP) server that works with Puch AI. It comes with ready-to-use tools for job searching and image processing.

MCP-Atlas evaluates how well AI agents use tools to complete real-world tasks, across 36 Model Context Protocol (MCP) servers in a reproducible Docker sandbox, scored with an LLM-as-judge.

Python implementation for building AI Agent with MCP (Model Context Protocol) tools and MCP server/client architecture.

This project demonstrates an Agent Development Kit (ADK) agent that interacts with a local SQLite database.

An Envoy-based gateway for Model Context Protocol (MCP) servers, enabling aggregation and routing of multiple MCP servers behind a single endpoint.

一个用于与语雀 API 集成的 Model-Context-Protocol (MCP) 服务器。此实现受 Figma-Context-MCP 的启发,并使用 语雀开放 API。

A production-ready for seamless integration between Wazuh SIEM and Large Language Models (LLMs).

Full documentation is available at buildkite.com/docs/apis/mcp-server.

Tanzu Platform Chat
Agent Skills

HTML output skill for Claude agents — 4 levels (Static Doc / Visual Artifact / Two-Way Interactive / Throwaway Tool). Based on Thariq Shihipar's framework.

claude-related skills or agent sharing.

AI Skills(ai-skills.ai)是一个面向各行各业的 AI 技能库。可直接用于openclaw,Hermes,qclaw,claude code,codex等智能体平台。为你的职业发展、行业竞争力,增加更多可能。

Bilibili tech-zone titles and cover big-text packs for 3–8 min videos: title formulas, 10 candidates, 3 cover sets, anti-pitfall list.

50+ consulting frameworks used by McKinsey, BCG, Bain, and Accenture — packaged as a Claude Code plugin

首次运行时,如果不存在 AiDoc/CodeReview/config.json,会交互式询问审核参数。后续运行自动读取配置。

Toss Tech Design 아티클을 참고해 만든 비공식 스킬 입니다.

Public subprocessors list page: table, update policy, no invented vendors.

Pressure-test research claims with falsifiable evidence plans, adversarial checks, frozen verifiers, and proof ledgers.

(▰˘◡˘▰) - AI Tamagotchi on Raspberry Pi. Agentic life-form with an E-Ink face

Multi-agent Claude Code skill for building apps and stuff

Mirror of https://cave.moxielogic.com/atgreen/secscan-skill