AI agents use wp_scaffold_theme to create or update resources in Wp Cli — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wp Cli environment.
This tool creates new files and directories (child theme scaffolding) which is a reversible write operation. While it modifies the WordPress environment by adding theme files, the changes can be undone by deleting the generated files. It does not execute arbitrary code, delete existing data irreversibly, or move money.
From the tool's definition Tool name 'wp_scaffold_theme' and description 'Generate a child theme skeleton' indicate creation of new theme files and directory structures on the filesystem.
Attacks that exploit this kind of access
Generate a child theme skeleton. It is categorised as a Write tool in the Wp Cli MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wp Cli MCP server in PolicyLayer and add a rule for wp_scaffold_theme: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Wp Cli. Nothing to install.
wp_scaffold_theme is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the wp_scaffold_theme rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for wp_scaffold_theme. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
wp_scaffold_theme is provided by the Wp Cli MCP server (mvtandas/wp-cli-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →