AI agents use wordpress_create_page to create or update resources in ItchWPMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ItchWPMCP environment.
This tool creates new content (pages) in WordPress, which is a reversible Write operation. While draft status provides safety guardrails, the tool can be used to generate unwanted pages that would require manual deletion. The blast radius is moderate—an AI agent could spam pages or create misleading content, but these can be undone.
From the tool's definition Tool creates a WordPress page via REST API. Description explicitly states 'Create a WordPress page' with 'draft status' default, indicating page creation capability.
Attacks that exploit this kind of access
Create a WordPress page. Defaults to draft status for safe review before publishing. It is categorised as a Write tool in the ItchWPMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ItchWP MCP server in PolicyLayer and add a rule for wordpress_create_page: 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 ItchWPMCP. Nothing to install.
wordpress_create_page 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 wordpress_create_page 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 wordpress_create_page. 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.
wordpress_create_page is provided by the ItchWP MCP server (manofsadness/itchwpmcp). 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 →