Clear the traffic log
AI agents call proxy_clear_traffic_log to permanently remove resources in Web Proxy MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a traffic log irreversibly removes historical data that cannot be recovered. This is a destructive action with potential compliance, forensic, and audit implications. While the blast radius is limited to logs (not financial or system operations), the permanent loss of records justifies 'Destructive' over 'Write'.
From the tool's definition Tool name is 'proxy_clear_traffic_log' and description states 'Clear the traffic log' — this permanently deletes log records without reversibility.
Attacks that exploit this kind of access
Clear the traffic log. It is categorised as a Destructive tool in the Web Proxy MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Web Proxy MCP Server MCP server in PolicyLayer and add a rule for proxy_clear_traffic_log: 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 Web Proxy MCP Server. Nothing to install.
proxy_clear_traffic_log 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 proxy_clear_traffic_log 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 proxy_clear_traffic_log. 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.
proxy_clear_traffic_log is provided by the Web Proxy MCP Server MCP server (mako10k/mcp-web-proxy). 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 →