Get a specific revision of a WordPress post.
AI agents call wordpress_get_revision to retrieve information from MCP Wordpress without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical version data of a post without modifying, deleting, or executing any operations. It is a read-only query that has no side effects, fitting the Read category. Severity is low because accessing revision history poses minimal direct risk to the WordPress site, though it could inform an attacker about content changes over time.
From the tool's definition Tool name indicates 'get' operation; description states 'Get a specific revision of a WordPress post' — a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Get a specific revision of a WordPress post. It is categorised as a Read tool in the MCP Wordpress MCP Server, which means it retrieves data without modifying state.
Register the MCP Wordpress MCP server in PolicyLayer and add a rule for wordpress_get_revision: 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 MCP Wordpress. Nothing to install.
wordpress_get_revision is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the wordpress_get_revision 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_get_revision. 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_get_revision is provided by the MCP Wordpress MCP server (crunchtools/mcp-wordpress). 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 →