Delete a wiki page. Requires admin authentication.
AI agents call delete_page_tool to permanently remove resources in MCP Mediawiki — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irrevers ibly deletes wiki page con tent, wh ich canno t be undone . Even though it requires auth entication , the action itself is des tructive and represents a high blast radius if misused by an AI agent, as entire pages and their history could be erased.
From the tool's definition Delete a wiki page. Requires admin authentication.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Delete a wiki page. Requires admin authentication. It is categorised as a Destructive tool in the MCP Mediawiki MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Mediawiki MCP server in PolicyLayer and add a rule for delete_page_tool: 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 Mediawiki. Nothing to install.
delete_page_tool is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_page_tool 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 delete_page_tool. 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.
delete_page_tool is provided by the MCP Mediawiki MCP server (mcp-mediawiki-crunchtools). 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 →