Discard all buffered browser errors.
AI agents call clear_errors to permanently remove resources in Pigeon — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently discards all buffered error data, which is irreversible. Once cleared, the historical error records are gone and cannot be recovered. This matches the Destructive category as it irreversibly deletes buffered data. Severity is medium because while the data loss could hinder debugging sessions, it doesn't affect production systems or user data directly.
From the tool's definition Discard all buffered browser errors
Attacks that exploit this kind of access
Discard all buffered browser errors. It is categorised as a Destructive tool in the Pigeon MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pigeon MCP server in PolicyLayer and add a rule for clear_errors: 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 Pigeon. Nothing to install.
clear_errors 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_errors 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_errors. 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_errors is provided by the Pigeon MCP server (pepperonas/pigeon). 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 →