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

Ratevert MCP is a public, read-only Model Context Protocol server for searching and converting currencies, stocks, crypto, ETFs, and funds.

An MCP (Model Context Protocol) server for AI voice synthesis with an inline audio player. Give your AI assistant a custom cloned voice!

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop.

This repository contains Python code examples for the Coursera course "AI Agents with Model Context Protocol."

Интеграционный сервер, использующий Model Context Protocol (MCP), для предоставления доступа к данным и функциям Bitrix24 для больших языковых моделей (LLM) и других AI-агентов.

medusa-mcp is a designed for integration with the Medusa JavaScript SDK. It provides a scalable backend layer for managing and interacting with Medusa’s data models, enabling automation,...

A MCP client for browser-use

A Model Context Protocol (MCP) server that provides seamless integration with OpenAI's GPT-5 API through Claude Code.

An MCP (Model Context Protocol) server for interacting with the Thermomix Cookidoo platform, built with fastmcp.

Remote MCP server with auth gated by Azure API Management

A Model Context Protocol (MCP) library for the Zig ecosystem.

MCPCorpus is a comprehensive dataset for analyzing the Model Context Protocol (MCP) ecosystem, containing ~14K MCP servers and 300 MCP clients with 20+ normalized metadata attributes.
Agent Skills

把「中文深度文配图方法论」+「可扩展 IP 角色库」打包的开源 Agent Skill。自带 ,装上挑一个就能给文章配图——。

A multi-platform agent skill that performs in-depth security scans and detects 20+ of the most common security vulnerabilities in your source code. Runs natively on , , and .

A coding agent for any model. Documentation

Nemotron Voice Agent Blueprint provides a comprehensive, end-to-end voice agent built with NVIDIA Nemotron state-of-the-art open models, as NVIDIA NIM for acceleration and scaling.

You're spending too much time on repetitive tasks:

xianxia-visual-director 是一个面向 Codex / Agent Skills 体系的东方仙侠环境视觉导演 Skill,用于把简短构想、已有提示词或视觉参考,扩展为结构清晰、可控、可衍生的电影级图片提示词。

Three Kings 2.2: compress with iMandalArt, address with BIRD, and publish with an A4 eight-page booklet.

一套面向 AI 编程助手的 ComfyUI + Anima 二次元生图技能包。当前主线是 v2mini:去掉多层代理式路由,只保留 Anima 生图所需的核心约束、Danbooru tag 精确校验和 ComfyUI 执行链路,让 AI 和人类把更多注意力留给画面本身。

Evaluate quality. Find the weakest link. Fix it. Prove it worked. Repeat.

Codex skill that turns a rough coding idea into a Codex /goal-ready contract.

Built for humans, AI agents, and CI/CD pipelines.

are modular packages of instructions, resources, and scripts that teach an agent to handle a specialized task. On disk, a skill is just a folder: a SKILL.