mcpField
E
EdgeOne Pages MCP

EdgeOne Pages MCP

FeaturedLocal
pages.edgeone.aiCloud & Infra440Updated 16w ago

About EdgeOne Pages MCP

EdgeOne Pages MCP is an MCP service for deploying full-stack projects to EdgeOne Makers and obtaining public URLs. It suits developers who need to publish projects or preview pages quickly, and it offers a remote option that requires no local installation.

Key features

  1. 01Deploys full-stack projects to EdgeOne Makers
  2. 02Returns publicly accessible URLs
  3. 03Quick preview of a single HTML page
  4. 04Streaming HTTP server without local installation

Use cases

  1. 01Publishing a single HTML page for quick preview
  2. 02Deploying a full-stack project to EdgeOne Makers and sharing its link

MCP support

This project is an MCP service that MCP clients can run locally through npx or reach through a Streaming HTTP remote endpoint to call deployment functions.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"edgeone-pages": {
"command": "npx",
"args": [
"-y",
"edgeone-pages-mcp"
]
}
}
}
Run commandnpx -y edgeone-pages-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmedgeone-pages-mcp

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
valuestringYesProvide the full HTML markup you wish to publish. After deployment, the system will generate and return a public URL where your content can be accessed.

Details

From the project README

EdgeOne Makers MCP

An MCP service for deploying full-stack projects to EdgeOne Makers and obtaining publicly accessible URLs.

Requirements

  • Node.js 18 or higher

MCP Configuration

// Tencent Cloud International (Default)
{
  "mcpServers": {
    "edgeone-makers-mcp-server": {
      "timeout": 600,
      "command": "npx",
      "args": ["@edgeone/makers-mcp@latest"],
      "env": {
        // Optional. 
        // If provided, skips the browser login flow.
        // How to obtain your API token: 
        // https://pages.edgeone.ai/document/api-token
        "EDGEONE_PAGES_API_TOKEN": "",
        // Optional. 
        // If provided, skips the browser project selection flow.
        "EDGEONE_PAGES_PROJECT_NAME": ""
      }
    }
  }
}

// Tencent Cloud China
{
  "mcpServers": {
    "edgeone-makers-mcp-server": {
      "timeout": 600,
      "command": "npx",
      "args": ["@edgeone/makers-mcp@latest", "--region", "china"],
      "env": {
        // Optional. 
        // If provided, skips the browser login flow.
        // How to obtain your API token: 
        // https://pages.edgeone.ai/document/api-token
        "EDGEONE_PAGES_API_TOKEN": "",
        // Optional. 
        // If provided, skips the browser project selection flow.
        "EDGEONE_PAGES_PROJECT_NAME": ""
      }
    }
  }
}

Quick HTML Preview

For quickly deploying a single HTML page for preview, use the Streaming HTTP MCP Server (no local installation required):

{
  "mcpServers": {
    "edgeone-makers-mcp-server": {
      "url": "https://mcp-on-edge.edgeone.site/mcp-server"
    }
  }
}

Source code: https://github.com/TencentEdgeOne/self-hosted-pages-mcp

License

MIT

Comments

Markdown supported

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.