Clear the captured XHR/fetch responses for a session.
AI agents call clear_network_capture to permanently remove resources in WebControl — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing captured network data is an irreversible operation; once the XHR/fetch responses are purged, that forensic/diagnostic information is gone. This fits Destructive rather than Write because the action overwrites/erases existing data with no undo path. Severity is medium since the blast radius is limited to session-level network capture logs rather than production data or financial systems.
From the tool's definition 'Clear the captured XHR/fetch responses' — permanently removes captured network data for a session, which cannot be recovered once cleared.
Attacks that exploit this kind of access
Clear the captured XHR/fetch responses for a session. It is categorised as a Destructive tool in the WebControl MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the WebControl MCP server in PolicyLayer and add a rule for clear_network_capture: 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 WebControl. Nothing to install.
clear_network_capture 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_network_capture 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_network_capture. 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_network_capture is provided by the WebControl MCP server (matansht/webcontrol). 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 →