AI agents use pfsense_replace_system_tunables to create or update resources in Pfsense — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pfsense environment.
This tool modifies system tunable parameters on a firewall, which are reversible configuration changes but can have significant impact on firewall behavior, performance, and security posture. It's not destructive (data can be reverted), but affects critical system settings. The high severity reflects that misconfigured tunables could disable security features or degrade firewall functionality.
From the tool's definition PUT /api/v2/system/tunables - PUT HTTP method indicates modification of system tunables via REST API. Description indicates this replaces/modifies system configuration parameters on pfSense firewalls.
Attacks that exploit this kind of access
PUT /api/v2/system/tunables. It is categorised as a Write tool in the Pfsense MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pfsense MCP server in PolicyLayer and add a rule for pfsense_replace_system_tunables: 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 Pfsense. Nothing to install.
pfsense_replace_system_tunables 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 pfsense_replace_system_tunables 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 pfsense_replace_system_tunables. 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.
pfsense_replace_system_tunables is provided by the Pfsense MCP server (abl030/pfsense-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 →