删除一个文件或目录。
AI agents call mcp_file_delete to permanently remove resources in ShowDoc MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of files or directories. Even though it operates on the local filesystem rather than application data, deletion cannot be undone and represents a destructive operation. An AI agent with access to this tool could accidentally or maliciously delete critical files, configuration, or source code.
From the tool's definition Tool name is 'mcp_file_delete' and description states '删除一个文件或目录' (delete a file or directory). The verb '删除' (delete) directly indicates irreversible removal of data.
Attacks that exploit this kind of access
删除一个文件或目录。. It is categorised as a Destructive tool in the ShowDoc MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ShowDoc MCP Server MCP server in PolicyLayer and add a rule for mcp_file_delete: 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 ShowDoc MCP Server. Nothing to install.
mcp_file_delete 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 mcp_file_delete 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 mcp_file_delete. 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.
mcp_file_delete is provided by the ShowDoc MCP Server MCP server (yfcyfc123234/showdoc_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 →