AI agents call get_pyfilter_code to retrieve information from Firegex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries the current Python filter source code for a service. It performs no modifications, deletions, code execution, or financial operations. The description explicitly uses the word 'Read' and indicates a passive retrieval operation. Even though it deals with security-sensitive filter code, the actual function is to query/fetch data, making it a Read category tool.
From the tool's definition Tool name 'get_pyfilter_code' and description 'Read the current Python filter source for a service' explicitly indicate a read operation that retrieves existing data without modification or side effects.
Attacks that exploit this kind of access
Read the current Python filter source for a service (empty string if unset). It is categorised as a Read tool in the Firegex MCP Server, which means it retrieves data without modifying state.
Register the Firegex MCP server in PolicyLayer and add a rule for get_pyfilter_code: 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.
get_pyfilter_code is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_pyfilter_code 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 get_pyfilter_code. 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.
get_pyfilter_code 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 →