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

OrigeneMCP is a core component of the OriGene ecosystem, a self-evolving multi-agent system designed to act as a virtual disease biologist.

Lightweight semantic code search engine — 2-stage vector + FTS + RRF fusion + MCP server for Claude Code

mcp - client 项目旨在把本地的mcp-server通过flask暴露出来,用户自建内网穿透,实现coze/dify/fastgpt等平台与本地资源进行交互。

>The most seeable and free way to control Microsof applications by AI model.

CROW - Your AI Agent. MCPs, OpenRouter, Any Model or local. It's your choice.

小红书自动评论工具(MCP Server) 这是一款基于 Playwright 开发的小红书自动搜索和评论工具,作为 MCP Server,可通过特定配置接入 MCP Client,帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布智能评论等操作。

A minimal MCP server built on crawl4ai for LLM-friendly web extraction

This project showcases how to use the MCP protocol with OpenAI, Azure OpenAI and GitHub Models. It provides a simple demo terminal application that interacts with a TODO list Agent.

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.

mcp-repl is an MCP server that gives an agent a persistent Python or R session, kept alive across tool calls.

Claude Code skills that let Claude interact with Web of Science (WoS) through Chrome DevTools MCP.

这是一个 mcp 服务器,提供大模型访问 boss 直聘部分接口的能力,让大模型替代用户人工筛选工作岗位并向 boss 打招呼
Agent Skills

A file-backed, spec-driven workflow for building real software with AI while staying in control.

Fourth girlfriend voting in progress - please vote on Issues.

OpenAI Codex CLI 0.128 introduced /goal — a persistent agent objective with runtime audit, token budget, and a soft-stop state machine. It can drive a single task for .

A growing collection of design skills for AI coding tools — Claude Code, Cursor, Codex, Windsurf, and anything else that reads a markdown rules file.

265 Rust rules your AI coding agent can use to write better code. Current for Rust 1.96 (2024 edition).

A reusable skeleton for an built on Hermes: a fleet of agents that items from sources, them, them against a rubric, them in parallel, each to a fulfillment path, pauses at , then — all coordinated on...

BenchFlow The universal environment framework — a benchmark is just a frozen environment.

End-to-End security platform for OpenClaw AI agents.

Claude Code skills for architecture, real estate, and workplace strategy. Type /skill-name and go.

本リポジトリは、ミノ駆動氏の公開資料を基に、設計判断の原則をAI Skillとして再構成する非公式プロジェクトです。ミノ駆動氏および所属組織による監修・承認・推奨を受けたものではありません。

AI agents Rules / Skills from Programming Books v0.5

这是 MathModel Skill 的 ,推荐能力较强、上下文充足、复杂推理和工具调用稳定的模型使用。Standard 提供 10 个协作 Skills、完整 S0-S8 流程、可追溯建模结果、原生 Word 公式、证据门禁和正式格式门禁。