【删除规则】删除一条项目规范规则。
AI agents call remove_rule to permanently remove resources in Prompts — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes project governance rules from the system. While the blast radius is limited to rule metadata rather than core application data, the irreversible deletion of configuration rules that guide project behavior qualifies it as Destructive. Severity is medium because accidental removal degrades project standards but does not compromise data integrity or cause direct financial harm.
From the tool's definition remove_rule deletes a project rule irreversibly; the description 【删除规则】 translates to 'delete rule', and removal of rules cannot be undone.
Attacks that exploit this kind of access
【删除规则】删除一条项目规范规则。. It is categorised as a Destructive tool in the Prompts MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Prompts MCP server in PolicyLayer and add a rule for remove_rule: 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 Prompts. Nothing to install.
remove_rule 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 remove_rule 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 remove_rule. 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.
remove_rule is provided by the Prompts MCP server (thana0623/pmcp-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 →