AI agents use wp_post_create 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 content in WordPress, which is a Write operation (reversible modification). While posts can be deleted afterward, the creation itself is a write action. Severity is high because an AI agent could create malicious posts, spam content, phishing pages, or defaced website content at scale if given uncontrolled use, potentially damaging site reputation and SEO.
From the tool's definition Tool creates new WordPress post, page, or custom post type entry with full HTML content support. Description explicitly states 'Create a new WordPress post' and 'Returns the new post ID', indicating irreversible data creation.
Attacks that exploit this kind of access
Create a new WordPress post, page, or custom post type entry. Returns the new post ID. Content supports full HTML. 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_post_create: 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_post_create 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_post_create 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_post_create. 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_post_create 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 →