Get the status of the watchdog file monitor for .rgignore hot reloading
AI agents call get_watchdog_status to retrieve information from RAGex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the operational state of an internal file monitoring component (.rgignore hot reloading). It performs a read-only operation that returns state information without creating, modifying, deleting, or executing anything. The absence of action verbs like 'set', 'update', 'execute', or 'delete' confirms it is a simple status retrieval.
From the tool's definition Tool name 'get_watchdog_status' and description 'Get the status of the watchdog file monitor' indicate a status query operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_watchdog_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAGex, and nothing reaches the server without passing your rules. This is the rule we recommend for get_watchdog_status:
{
"version": "1",
"default": "deny",
"tools": {
"get_watchdog_status": {}
}
}get_watchdog_status is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the status of the watchdog file monitor for .rgignore hot reloading. It is categorised as a Read tool in the RAGex MCP Server, which means it retrieves data without modifying state.
Register the RAGex MCP server in PolicyLayer and add a rule for get_watchdog_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 RAGex. Nothing to install.
get_watchdog_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 get_watchdog_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 get_watchdog_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.
get_watchdog_status is provided by the RAGex MCP server (jbenshetler/mcp-ragex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAGex, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 RAGex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.