清空计算历史
AI agents call clear_calculation_history to permanently remove resources in Math Calculation MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing/purging history is an irreversible destructive action. Once the calculation history is wiped, it cannot be recovered. Severity is medium because the blast radius is limited to stored calculation logs rather than critical data or systems.
From the tool's definition 清空计算历史 (clear calculation history) — the tool name and description indicate irreversible deletion of stored calculation history
Attacks that exploit this kind of access
清空计算历史. It is categorised as a Destructive tool in the Math Calculation MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Math Calculation MCP Server MCP server in PolicyLayer and add a rule for clear_calculation_history: 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 Math Calculation MCP Server. Nothing to install.
clear_calculation_history 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 clear_calculation_history 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 clear_calculation_history. 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.
clear_calculation_history is provided by the Math Calculation MCP Server MCP server (k-summer/math_mcps). 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 →