get_worker_status
AI agents call get_worker_status to retrieve information from Claude Operator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of worker sessions without modifying or executing anything. It is a monitoring/inspection operation typical of orchestration systems. The empty description lowers confidence slightly, but the naming convention and server architecture strongly indicate read-only semantics. Status queries have minimal blast radius if misused by an autonomous agent.
From the tool's definition Tool name 'get_worker_status' implies retrieving status information about worker sessions. The verb 'get' is a read-only retrieval operation.
Attacks that exploit this kind of access
get_worker_status. It is categorised as a Read tool in the Claude Operator MCP Server, which means it retrieves data without modifying state.
Register the Claude Operator MCP server in PolicyLayer and add a rule for get_worker_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 Claude Operator. Nothing to install.
get_worker_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_worker_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_worker_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_worker_status is provided by the Claude Operator MCP server (moygulati/claude-operator). 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 →