经 AI Skill Hub 精选评估，MCP工具：人机界面 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.5 分，适合有一定技术背景的用户使用。
MCP工具：人机界面 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
MCP工具：人机界面 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/ggui-ai/ggui
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp-------": {
"command": "npx",
"args": ["-y", "ggui"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例： 用户: 请帮我用 MCP工具：人机界面 执行以下任务... Claude: [自动调用 MCP工具：人机界面 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入："列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp_______": {
"command": "npx",
"args": ["-y", "ggui"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset=".github/logo-dark.svg" /> <img src=".github/logo-light.svg" alt="ggui — generative graphical user interface" width="480" /> </picture> </p>
<p align="center"><strong>ggui</strong> is the universal MCP-UI protocol — a runtime-negotiated data contract between AI agents and human users.</p>
<p align="center"> <a href="https://docs.ggui.ai">Docs</a> · <a href="https://docs.ggui.ai/oss-quickstart/">OSS Quickstart</a> </p>
🚧 Active development — v0.1.0-rc.1 is the first published release candidate. APIs are converging; pin exact versions and watch Releases for the next RC and the v0.1.0 final.
---
Agents describe what they need in natural language; ggui generates ephemeral, interactive interfaces over MCP. No frontend code, no React templates, no custom components — agents talk, users see UI.
This repo is the open protocol + reference runtime. Self-host with ggui serve; pair against any MCP-aware agent runtime (Claude Desktop, Claude Code, Cursor, ChatGPT desktop, Goose, your own). Zero account required, zero managed infrastructure required, zero cloud dependency.
npm install -g @ggui-ai/cli ggui serve ```
ggui serve stands up @ggui-ai/mcp-server with the first-run bundle: MCP at /mcp, the same-origin session viewer at /r/<shortCode>, pairing endpoints, and a live-channel WebSocket. Open http://127.0.0.1:6781/ to land on the operator console.
Point any MCP-compatible agent runtime at http://127.0.0.1:6781/mcp with Authorization: Bearer dev. The OSS Quickstart walks through the full self-hosted path including pairing.
```bash
samples/ holds end-to-end examples you can clone:
samples/gguis/ — ready-to-run project configs (default, leaflet-demo, mapbox-demo, canvas-demo) showing how a ggui.json is shaped.samples/agents/ — reference agent that hosts ggui as an MCP server (Claude Agent SDK).samples/gadgets/ — example component / hook gadgets for the marketplace.samples/mcp-servers/ — minimal domain MCP servers (e.g. a todo server) you can pair against.If your agent runtime supports MCP natively, skip the SDK entirely. Add ggui serve as an MCP server:
{
"mcpServers": {
"ggui": {
"url": "http://127.0.0.1:6781/mcp",
"headers": { "Authorization": "Bearer dev" }
}
}
}The runtime's native tool-calling loop discovers ggui_push, ggui_update, and the blueprint catalogue tools directly. Working examples per framework: Claude, OpenAI, Gemini, generic MCP.
Consumer-facing surface — what you npm install:
| Package | Purpose | npm |
|---|---|---|
[@ggui-ai/cli](./packages/ggui-cli) | The ggui binary — ggui serve, ggui dev, ggui blueprint | [](https://npmjs.com/package/@ggui-ai/cli) |
[@ggui-ai/mcp-server](./packages/mcp-server) | Reference OSS server (programmatic embedding) | [](https://npmjs.com/package/@ggui-ai/mcp-server) |
[@ggui-ai/react](./packages/ggui-react) | React embedding — <McpAppIframe> + shells | [](https://npmjs.com/package/@ggui-ai/react) |
[@ggui-ai/react-native](./packages/ggui-react-native) | React Native embedding — WebView-backed renderer | [](https://npmjs.com/package/@ggui-ai/react-native) |
[@ggui-ai/protocol](./packages/protocol) | Wire types (events, sessions, WebSocket, MCP envelopes) | [](https://npmjs.com/package/@ggui-ai/protocol) |
[@ggui-ai/gadgets](./packages/gadgets) | Author wrappers for 3rd-party libs (Leaflet, Mapbox, …) | [](https://npmjs.com/package/@ggui-ai/gadgets) |
Plus ~30 supporting packages under packages/ spanning the runtime (@ggui-ai/mcp-server-core, @ggui-ai/mcp-server-handlers, @ggui-ai/ui-gen, @ggui-ai/negotiator), authoring (@ggui-ai/project-config, @ggui-ai/ui-registry, @ggui-ai/predefined), registry (@ggui-ai/registry-core, @ggui-ai/registry-server), and dev tooling (@ggui-ai/dev-stack, @ggui-ai/agent-runtime, @ggui-ai/console). See each subdirectory for details.
MCP工具是一个开源的人机界面工具，提供了一个通用的接口层，用于生成人机界面。虽然工具的代码质量和设计良好，但仍然存在一些缺陷和不足。需要进一步优化和完善。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
AI Skill Hub 点评：MCP工具：人机界面 的核心功能完整，质量良好。对于Claude Desktop / Claude Code 用户来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | ggui |
| Topics | mcpagent-frameworkagent-uiagentsaigenerative-uitypescript |
| GitHub | https://github.com/ggui-ai/ggui |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间：2026-05-23 · 更新时间：2026-05-23 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端