About @demoway/mcp-server
@demoway/mcp-server connects DemoWay page captures to AI workflows, helping teams revise existing pages or generate designs and frontend code. It supports searching demo pages and downloading captured HTML formatted for AI use.
Key features
- 01Search demo pages by keyword
- 02Download captured pages as AI-friendly HTML
Use cases
- 01Find a page in a DemoWay demo
- 02Export captured pages for AI modification
MCP support
The MCP server exposes tools to search DemoWay demo pages and download captured page HTML. It requires the DemoWay browser extension and a DemoWay API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
4Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | demo page url |
| keyword | string | Yes | Search keyword |
Details
From the project README@demoway/mcp-server
DemoWay MCP Server allows you to provide an existing single page or all pages in a functional flow to the AI for further modification, generating new page designs or frontend code.
You need to install the DemoWay browser extension to use it with the DemoWay MCP Server.
Available Tools
download_demo_step_pretty_html: Download the captured pages in an AI-friendly HTML format to your local computer for further modification by AIsearch_demo_step: Search for a specific page by keyword in the specified demo
Usage
Configuration
For Mac/Linux User
{
"mcpServers": {
"demoway": {
"command": "npx",
"args": ["-y", "@demoway/mcp-server@latest"],
"env": {
"DEMOWAY_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
For Windows User
{
"mcpServers": {
"demoway": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@demoway/mcp-server"],
"env": {
"DEMOWAY_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
You can get the DEMOWAY_API_KEY from the dashboard in DemoWay.
Detailed Guide
License
MIT ©DemoWay
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.