Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@HTML Deploy MCP Server Create a simple contact form and deploy it."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
一个基于 FastAPI 的 MCP 服务器，可将 HTML 页面代码一键部署到在线预览平台，返回可访问的 URL。
🚀 一键部署 HTML 页面到在线服务器
🔗 返回可直接访问的预览链接
🤖 支持 MCP 协议，可与 Claude、Cursor 等 AI 工具集成
Related MCP server: publish-artifacts-mcp
Python 3.12+
# 克隆项目
git clone https://github.com/luler/hello_project_mcp.git
cd hello_project_mcp
# 安装依赖
pip install -r requirements.txtpython main.py服务将在 http://localhost:8989 启动。
端点 | 协议 | 用途 |
| HTTP | Streamable HTTP 传输 |
| SSE | Server-Sent Events 传输 |
编辑配置文件：
{
"mcpServers": {
"html-deploy": {
"url": "http://localhost:8989/sse"
}
}
}在 Cursor 设置中添加 MCP 服务器：
{
"mcpServers": {
"html-deploy": {
"url": "http://localhost:8989/sse"
}
}
}使用 SSE 端点：http://localhost:8989/sse
配置完成后，在 AI 对话中可以这样使用：
帮我做一个贪吃蛇游戏，用 deploy_html 部署，给我链接创建一个渐变背景的登录页面，然后部署上线写一个动态时钟页面，deploy_html 发布一下AI 会自动生成 HTML 代码并调用 deploy_html 工具进行部署，返回预览链接。
启动服务后访问：
Swagger UI: http://localhost:8989/docs
ReDoc: http://localhost:8989/redoc
部署 HTML 页面到预览服务器。
请求：
{
"html": "<!DOCTYPE html><html>...</html>"
}响应：
{
"success": true,
"message": "HTML打包并上传成功",
"preview_url": "https://html.luler.top/preview/xxxxx"
}通过环境变量或 .env 文件配置：
UPLOAD_PLATFORM_BASE_URL=https://html.luler.top # 预览平台地址
UPLOAD_CODE=1dec7206c6 # 项目标识
PORT=8989 # 服务端口
DEBUG=0 # 调试模式（1为开启热重载）This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Publish AI-generated HTML & Markdown to a hosted, shareable URL via MCP.
Publish HTML, files, or a URL to a permanent public URL, then update it — from any MCP agent.
Create sandboxed public-unlisted or access-key-protected HTML previews through a remote MCP server.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/luler/hello_project_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server