★开跑前先调这个自检:浏览器(marionette)连没连、当前 worker provider/model、worker key 配没配。
AI agents call frx_status to retrieve information from Frx Director without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about the Firefox browser connection, worker model configuration, and key setup. It performs no mutations, code execution, or side effects—purely diagnostic querying. It is a Read operation with low severity due to its informational nature and no capability to affect system state.
From the tool's definition Tool name 'frx_status' and description describing a self-check that queries browser connection status ('浏览器(marionette)连没连'), current worker provider/model, and configuration state ('worker key 配没配').
Attacks that exploit this kind of access
★开跑前先调这个自检:浏览器(marionette)连没连、当前 worker provider/model、worker key 配没配。. It is categorised as a Read tool in the Frx Director MCP Server, which means it retrieves data without modifying state.
Register the Frx Director MCP server in PolicyLayer and add a rule for frx_status: 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 Frx Director. Nothing to install.
frx_status 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 frx_status 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 frx_status. 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.
frx_status is provided by the Frx Director MCP server (whitenightshadow/frx-director-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 →