Set CRS paranoia level (1-4). Level 1 is minimal rules, level 4 is maximum security with more false positives.
AI agents use waf_set_paranoia to create or update resources in WAF MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your WAF MCP Server environment.
This tool modifies the WAF's global security configuration by changing the CRS paranoia level. It is reversible (can be set back to a different level), placing it in Write rather than Destructive.
From the tool's definition Set CRS paranoia level (1-4). Level 1 is minimal rules, level 4 is maximum security with more false positives.
Attacks that exploit this kind of access
Set CRS paranoia level (1-4). Level 1 is minimal rules, level 4 is maximum security with more false positives. It is categorised as a Write tool in the WAF MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the WAF MCP Server MCP server in PolicyLayer and add a rule for waf_set_paranoia: 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 WAF MCP Server. Nothing to install.
waf_set_paranoia is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the waf_set_paranoia 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 waf_set_paranoia. 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.
waf_set_paranoia is provided by the WAF MCP Server MCP server (kratosuae/waf_mcp). 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 →