EdgeOne Pages MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EDGEONE_PAGES_API_TOKEN | No | Optional. Your EdgeOne Pages API token, required to deploy folders or zip files to projects. Instructions: https://edgeone.ai/document/177158578324279296 | |
| EDGEONE_PAGES_PROJECT_NAME | No | Optional. Provide a project name to update an existing project, or leave empty to create a new EdgeOne Pages project. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| deploy_htmlC | Deploy HTML content to EdgeOne Pages, return the public URL |
| deploy_folder_or_zipC | Deploy a built frontend directory (or zip file) to EdgeOne Pages. Returns: the deployment URL and project metadata. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: deploy_folder_or_zip handles directory or zip file deployments for built frontends, while deploy_html handles direct HTML content deployments. There is no overlap or ambiguity between them.
Both tools follow a consistent verb_noun pattern starting with 'deploy_' and clearly indicate their target (folder_or_zip vs. html). The naming is uniform and predictable throughout the set.
With only 2 tools, the server feels thin for a deployment service. It lacks essential operations like listing deployments, updating or deleting them, or managing projects, which limits agent workflows and creates dead ends.
The toolset is severely incomplete for a deployment domain. It provides create-like operations (deploy) but lacks read, update, delete, or management functions (e.g., list_deployments, get_deployment_status, delete_deployment), making it difficult for agents to handle full lifecycle tasks.