AI agents use set_pyfilter_code_from_file to create or update resources in Firegex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Firegex environment.
This tool creates or modifies firewall filter rules by uploading Python code to Firegex. While not destructive (the change is reversible via deletion or update), it is clearly a Write operation that alters security-critical firewall state. Severity is high because misuse could disable or weaken security controls, affect network traffic routing, or introduce malicious filtering logic into a CTF/proxy firewall system.
From the tool's definition Tool description states 'Load Python filter code from a local file and push it to Firegex.' The verb 'push' indicates modification of firewall configuration on a live system. The tool modifies filter rules rather than merely reading them.
Attacks that exploit this kind of access
Load Python filter code from a local file and push it to Firegex. It is categorised as a Write tool in the Firegex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Firegex MCP server in PolicyLayer and add a rule for set_pyfilter_code_from_file: 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 Firegex. Nothing to install.
set_pyfilter_code_from_file 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 set_pyfilter_code_from_file 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 set_pyfilter_code_from_file. 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.
set_pyfilter_code_from_file is provided by the Firegex MCP server (umbra2728/firegex-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 →