get_engine_status
AI agents call get_engine_status to retrieve information from Claude Voice Commands without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Status checks are informational reads with no side effects. Without a description, confidence is reduced but the naming convention clearly indicates a read operation that simply returns the current status of the voice processing engine. No data is created, modified, deleted, or executed.
From the tool's definition Tool name 'get_engine_status' indicates it retrieves status information without modifying any state. No description provided, but the name and server context (voice command system) suggest this queries the current operational state of the audio/transcription…
Attacks that exploit this kind of access
get_engine_status. It is categorised as a Read tool in the Claude Voice Commands MCP Server, which means it retrieves data without modifying state.
Register the Claude Voice Commands MCP server in PolicyLayer and add a rule for get_engine_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 Voice Commands. Nothing to install.
get_engine_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_engine_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_engine_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_engine_status is provided by the Claude Voice Commands MCP server (jwitcoff/claude_chat). 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 →