AI agents call get_nfproxy_service 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 retrieves configuration or status information about a specific nfproxy service by its identifier. The verb 'Get' and lack of any modification, deletion, or execution language confirms this is a read-only query. No data is created, modified, deleted, or executed—only fetched. The blast radius of misuse is minimal (information disclosure only), making severity low.
From the tool's definition Tool name 'get_nfproxy_service' and description 'Get a single nfproxy service by id' indicates a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a single nfproxy service by id. 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_nfproxy_service: 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_nfproxy_service 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_nfproxy_service 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_nfproxy_service. 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_nfproxy_service 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 →