Open a WordPress post for collaborative editing
AI agents call wp_open_post to retrieve information from Claudaborative Editing without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Opening a post for editing is primarily a read operation that retrieves post content and prepares it for editing. While it initiates an editing session, the act of opening itself does not modify, create, or delete data. Severity is low as it only exposes existing content to the editing context.
From the tool's definition 'Open a WordPress post for collaborative editing' — the action described is opening/loading a post, which is a read/retrieval operation
Documented attack patterns abuse exactly the kind of access wp_open_post gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claudaborative Editing, and nothing reaches the server without passing your rules. This is the rule we recommend for wp_open_post:
{
"version": "1",
"default": "deny",
"tools": {
"wp_open_post": {}
}
}wp_open_post is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Open a WordPress post for collaborative editing. It is categorised as a Read tool in the Claudaborative Editing MCP Server, which means it retrieves data without modifying state.
Register the Claudaborative Editing MCP server in PolicyLayer and add a rule for wp_open_post: 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 Claudaborative Editing. Nothing to install.
wp_open_post 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 wp_open_post 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_open_post. 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_open_post is provided by the Claudaborative Editing MCP server (pento/claudaborative-editing). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claudaborative Editing, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 Claudaborative Editing tools catalogued and risk-classified — across an index of 43,000+ MCP servers.