AI agents use wp_term_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 performs a reversible write operation—it creates new taxonomy terms (categories, tags, or custom taxonomies) which are stored in the database but can be deleted or modified. The severity is 'medium' rather than 'high' because while it modifies WordPress taxonomy data structure, it does not directly impact user-facing content, financial operations, or enable arbitrary code execution.
From the tool's definition Tool creates a new term in a taxonomy (category, tag, or custom taxonomy). The description explicitly states 'Create a new term', which is a write operation that adds data to WordPress taxonomy structures.
Attacks that exploit this kind of access
Create a new term in a taxonomy (category, tag, or custom taxonomy). 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_term_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_term_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_term_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_term_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_term_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 →