按 HTTP 方法过滤（GET / POST / PUT / DELETE 等），返回精简视图。
AI agents call filter_by_method to permanently remove resources in Charles MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call filter_by_method doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Charles MCP Server is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
按 HTTP 方法过滤（GET / POST / PUT / DELETE 等），返回精简视图。. It is categorised as a Destructive tool in the Charles MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Charles MCP Server MCP server in PolicyLayer and add a rule for filter_by_method: 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 Charles MCP Server. Nothing to install.
filter_by_method 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 filter_by_method 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 filter_by_method. 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.
filter_by_method is provided by the Charles MCP Server MCP server (tianhetonghua/charles-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.