MCP (Model Context Protocol) is an open protocol that enables AI models to securely interact with local and remote resources.
Just perform unified configuration on clients that support MCP (such as Cline, Cursor, Claude, etc.). OpenAI announced in March 2025 that it supports the MCP protocol, enabling this feature to be widely used on all mainstream AI platforms.
EdgeOne Pages Deploy MCP
EdgeOne Pages Deploy MCP is a dedicated service that can quickly Deploy Web static resource content to EdgeOne Pages and generate a public access link. This enables you to immediately preview and share AI-generated webpage content or products after project building.
Deploy an HTML single file
Deploy a folder or ZIP package
Configuration Method
In any client that supports MCP, you can use the following two methods of JSON configuration to quickly integrate Pages Deploy MCP Server.
Based on Standard Input/Output
This is also the current implementation method for most MCP Servers. Just add a few lines of simple configuration in applications that support MCP, and you can start a fully - featured web page rapid deployment service. This allows AI to publish the completed web page code to edge nodes and provide an accessible URL.
Notes:
Note: When AI calls Pages Deploy MCP Server to Deploy a single html file, only a temporary link will be generated. If you want to associate a Pages Project, you need to clearly tell AI to Deploy a certain folder or ZIP compressed package.
{
"mcpServers":{
"edgeone-pages-mcp-server":{
"command":"npx",
"args":["edgeone-pages-mcp"],
"env":{
// Optional. If you need to deploy a folder or a ZIP compressed package, the API Token is required.
"EDGEONE_PAGES_API_TOKEN":"",
// Optional. Leave blank to create a new Pages Project, or fill in an existing project name to update the project.
"EDGEONE_PAGES_PROJECT_NAME":""
}
}
}
}
Supported clients: Cursor, VSCode, Windsurf, ChatWise, Cheery Studio
Based on Streamable HTTP
Stdio is convenient, but since it depends on specific clients, there are also certain potential security risks. Therefore, performing remote calls through Streamable HTTP will become the future trend of MCP Server.
As shown below, you only need to specify the remote endpoint.
Note: Deployment of folders or ZIP packages is not supported via the Streamable HTTP method.
Technical Principles
The Pages MCP Server leverages serverless edge computing capability and KV storage. By receiving HTML content through API, it can automatically generate a public access link that takes effect immediately, implement second-level static page deployment, and has a built-in error handling mechanism.
Build 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 simple configurations in editors such as Cursor to enable it. When the AI needs to obtain the user's geographic location, it can automatically obtain this information through the get_geo API, then recommend nearby restaurants or scenic spots.
Remote MCP Server
After the second edition of the MCP Server protocol was finalized, we immediately upgraded this dedicated service for Pages to support Streamable HTTP. Access 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 through 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 the API_KEY
MCP's technology trends are highly compatible 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 the need to manage infrastructure. We will continuously follow the industry dynamics, combine with the technical evolution direction of the community, continuously enhance MCP's relevant capabilities, and help developers improve efficiency and development experience.
For more details about Pages, view other chapters in the document.