AI agents use acf_update_fields to create or update resources in Wordpress — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wordpress environment.
This tool creates or modifies ACF (Advanced Custom Fields) metadata on WordPress posts/pages. It is a Write operation because it reverses changes (fields can be updated again). Severity is medium because unintended field modifications could corrupt post metadata or trigger dependent business logic, but changes are reversible.
From the tool's definition Tool name 'acf_update_fields' and description explicitly states 'Use to update ACF custom fields' — a modification operation. Description confirms 'Write' categorization and notes it is 'blocked by WP_READ_ONLY', indicating it modifies data.
Attacks that exploit this kind of access
Use to update ACF custom fields for a post or page. Write — blocked by WP_READ_ONLY. It is categorised as a Write tool in the Wordpress MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wordpress MCP server in PolicyLayer and add a rule for acf_update_fields: 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 Wordpress. Nothing to install.
acf_update_fields 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 acf_update_fields 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 acf_update_fields. 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.
acf_update_fields is provided by the Wordpress MCP server (@adsim/wordpress-mcp-server). 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 →