Edge Developer Platform
  • Pages
    • Product Introduction
    • Quick Start
      • Importing a Git Repository
      • Starting From a Template
      • Direct Upload
    • Framework Guide
      • Frontends
      • Backends
      • Full-stack
        • Next.js
    • Project Guide
      • Project Management
      • edgeone.json
      • Configuring Cache
      • Error Codes
    • Build Guide
    • Deployment Guide
      • Overview
      • Create Deploys
      • Manage Deploys
      • Deploy Button
      • Use Github Actions
      • Using CNB Plugin
      • Using IDE Plug-In
      • Using CodeBuddy IDE
    • Domain Management
      • Overview
      • Custom Domain
      • Configuring an HTTPS Certificate
      • How to Configure a DNS CNAME Record
    • Pages Functions
      • Overview
      • Edge Functions
      • Node Functions
    • Log Analysis
    • KV Storage
    • Edge AI
    • API Token
    • EdgeOne CLI
    • Pages MCP
    • Integration Guide
      • AI
        • Dialogue Large Models Integration
        • Large Models for Images Integration
      • Database
        • Supabase Integration
        • Pages KV Integration
      • Ecommerce
        • Shopify Integration
        • WooCommerce Integration
      • Payment
        • Stripe Integration
        • Integrating Paddle
      • CMS
        • WordPress Integration
        • Contentful Integration
        • Sanity Integration
      • Authentication
        • Supabase Integration
        • Clerk Integration
    • Best Practices
      • Using General Large Model to Quickly Build AI Application
      • Use the Deepseek-R1 model to quickly build a conversational AI site
      • Building an Ecommerce Platform with WordPress + WooCommerce and GatsbyJS
      • Building a SaaS Site Using Supabase and Stripe
      • Building a Company Brand Site Quickly
      • How to Quickly Build a Blog Site
    • Migration Guides
      • Migrating from Vercel to EdgeOne Pages
      • Migrating from Cloudflare Pages to EdgeOne Pages
      • Migrating from Netlify to EdgeOne Pages
    • Troubleshooting
    • FAQs
    • Contact Us
    • Release Notes
Docs Overview/
Edge Developer Platform/
Pages/
Pages MCP/

Pages MCP

What Is MCP?

MCP (Model Context Protocol) is an open protocol that enables AI models to securely interact with both local and remote resources.

Just perform unified configuration on clients that support MCP (such as Cline, Cursor, Claude, etc.). OpenAI announced support for the MCP protocol in March 2025, making this feature widely used on all mainstream AI platforms.


EdgeOne Pages Deploy MCP

EdgeOne Pages Deploy MCP is a dedicated service that enables fast deployment of Web static resource content to EdgeOne Pages and generates public access links. This allows you to immediately preview and share AI-generated webpage content or products after project build.

Deploy HTML single file




Deploy folder or ZIP package



Configuration Method

In any client that supports MCP, you can use the following two JSON configurations to quickly integrate Pages Deploy MCP Server.


Based on Stdio (Standard Input/Output)

This is also the implementation method for most MCP Servers currently. Just add a few lines of simple configuration in applications that support MCP to launch a fully-optimized web page fast deployment service, allowing AI to publish completed web code to edge nodes and provide an accessible URL.
Notes:
AI calls Pages Deploy MCP Server to Deploy a single html file, only generating a temporary link. If you want to associate a Pages project, you need to clearly tell AI to Deploy a specific folder or ZIP compressed package.
The method for obtaining EDGEONE_PAGES_API_TOKEN can be found in the referenced document API Token.
{
  "mcpServers": {
    "edgeone-pages-mcp-server": {
      "command": "npx",
      "args": ["edgeone-pages-mcp"],
      "env": {
        // Optional. If deploying a folder or ZIP package, the API Token is required.
        "EDGEONE_PAGES_API_TOKEN": "",
        // Optional, leaving it empty will create a new Pages Project, filling in an existing project name will update the project
        "EDGEONE_PAGES_PROJECT_NAME": ""
      }
    }
  }
}
Supported clients: Cursor, VSCode, Windsurf, ChatWise, Cheery Studio, etc.


Based on Streamable HTTP

Stdio is convenient but has certain security risks due to its dependency on specific clients. Therefore, performing remote calls via Streamable HTTP will become the future trend for MCP Server.

As shown below, just specify the remote endpoint.
{
  "mcpServers": {
    "edgeone-pages-mcp-server": {
      "url": "https://mcp-on-edge.edgeone.app/mcp-server"
    }
  }
}
Supported clients: ChatWise
Notes:
Note: Deployment of folders or ZIP packages is not supported via HTTP method.


Technical Principles

Pages MCP Server leverages serverless edge computing capabilities and KV storage, receives HTML content through API, automatically generates publicly accessible links that take effect immediately, enables second-level static page deployment with built-in error handling mechanisms.



Building Your Own MCP Service

In summary, MCP allows AI to access more resources and call more tools during the dialogue. Below, we use two examples for a quick start to deploy your own MCP Server.


Local MCP Server

You can use the MCP Geo geographic location MCP template for one-click deployment, then add a few lines of simple configuration in editors such as Cursor to enable it. When AI needs to obtain user geographic location, it can automatically get this information through the get_geo API, then recommend nearby restaurants or scenic spots.


Remote MCP Server

After the protocol for the second edition of the MCP Server was finalized, we immediately upgraded this dedicated service for Pages to support Streamable HTTP. Visit https://mcp-on-edge.edgeone.app/ to experience the web version of MCP.

You can also quickly deploy the MCP Client and MCP Server implemented based on EdgeOne edge functions using the MCP on Edge template. The environment variables API_KEY, BASE_URL, and MODEL in it are compatible with the OpenAI API specification, which means you can directly configure these variables according to the official usage method of OpenAI.

The following table provides several references for obtaining an API_KEY
:
Platform
BASE_URL
API_KEY (document address)
MODEL (example model ID)
https://openrouter.ai/api/v1
https://openrouter.ai/settings/keys
anthropic/claude-3.7-sonnet
https://api.deepinfra.com/v1/openai
https://deepinfra.com/dash/api_keys
anthropic/claude-3-7-sonnet-latest
https://api.deepseek.com/v1
https://platform.deepseek.com/api_keys
deepseek-chat



Why Use EdgeOne Pages?

The technical trends of MCP are highly aligned with the edge serverless architecture of Pages Functions. Its advantages in performance, scalability, and ease of use allow developers to enjoy the convenience of the global edge network without the need to manage infrastructure. We will continuously follow industry dynamics, combine with the evolution direction of community technology, continuously enhance MCP's relevant capabilities, and help developers improve efficiency and development experience.

For more details about Pages, view the document other chapters.