Product Introduction
Quick Start
- Importing a Git Repository
- Starting From a Template
- Direct Upload
- Start with AI
Framework Guide
- Frontends
- Backends
- Full-stack
  - Next.js
- Custom 404 Page
Project Guide
- Project Management
- edgeone.json
- Configuring Cache
- Error Codes
Build Guide
Deployment Guide
- Overview
- Create Deploys
- Manage Deploys
- Deploy Button
- Using Github Actions
- Using CNB Plugin
- Using IDE PlugIn
- 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

Pages MCP

What Is MCP
MCP (Model Context Protocol) is an open protocol that enables AI models to securely interact with local and remote resources. Just configure it in MCP-supported clients such as Cline, Cursor, and Claude.
﻿
EdgeOne Pages Deploy MCP
EdgeOne Pages Deploy MCP is a dedicated service that enables quick deployment of Web applications to EdgeOne Pages and generates public access links. This allows you to immediately preview and share AI-generated Web content.
﻿
Deployment Mode
Pages Deploy MCP Server supports two deployment methods. Based on your project condition, you can quickly deploy projects to Pages in any MCP-supported client. 
﻿
Deploying Full-Stack Application
Use natural language to communicate with AI, guide it to complete coding and deploy projects to Pages for continuous development and iteration. It is recommended to use the AI context file provided by Pages to help AI generate code that conforms to standards. For details, refer to Documentation.
﻿
{
  "mcpServers": {
    "edgeone-pages-mcp-server": {
      "command": "npx",
      // deployment needed to Tencent Cloud China site, use ["edgeone-pages-mcp-fullstack", "--region", "china"]
      "args": ["edgeone-pages-mcp-fullstack"]
    }
  }
}
﻿
Supported clients: Cursor, VSCode, Windsurf, ChatWise, Cheery Studio, and others.
﻿
Sharing HTML Content
Deploy HTML content to Pages without logging in, for example, share AI-generated web content.
{
  "mcpServers": {
    "edgeone-pages-mcp-server": {
      "url": "https://mcp-on-edge.edgeone.app/mcp-server"
    }
  }
}
Supported clients: ChatWise
﻿
This method leverages serverless edge computing capability and KV storage to receive HTML content through API, automatically generating a public access link that takes effect immediately, achieving static page deployment in seconds with a built-in error handling mechanism.
﻿
﻿
﻿
Deploying Your Own MCP Service
Pages also provides templates to help you quickly start deploying your own MCP Server.
﻿
Take Self Hosted Pages MCP as an example. This is the MCP Server template for sharing HTML content mentioned above. You can deploy it as your own project to use your own domain name and learn the development paradigm of the MCP protocol.
Pre-issues:
1. Configure KV storage: used to store HTML content. The variable name for the bound KV namespace must be my_kv. Redeploy the project after binding. For more ways to use KV, see KV storage.
2. Bind a custom domain: Obtain an exclusive access address. For details, see custom domain name.
﻿
After deployment, add the following content in the MCP Server configuration file:
{
  "mcpServers": {
    "edgeone-pages": {
      "url": "https://yourcustomdomainname/mcp-server"
    }
  }
}
﻿
Deploy HTML content to Pages through natural language with AI; you can also deploy through API, for example:
curl -X POST https://your-custom-domain-name/kv/set \  -H "Content-Type: application/json" \  -d '{"value": "<html><body><h1>Hello, World!</h1></body></html>"}'
﻿
﻿
Why Use EdgeOne Pages
MCP technology trends align well with the edge serverless architecture of Pages Functions. Its advantages in performance, scalability, and ease of use enable developers to enjoy the convenience of the Global Edge Network without managing infrastructure. We will continue to follow industry updates, combine them with the evolution of community technology, and continuously enhance MCP capabilities to help developers improve efficiency and development experience.
﻿
For more details about Pages, view the document in other chapters.

What Is MCP
EdgeOne Pages Deploy MCP
Deployment Mode
- Deploying Full-Stack Application
- Sharing HTML Content
Deploying Your Own MCP Service
Why Use EdgeOne Pages