AI agents call voice_status to retrieve information from Jarvis MCP 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 and pending input data without creating, modifying, deleting, or executing any operations. It is purely informational and has no side effects. The low severity reflects minimal blast radius—misuse would only expose voice system state information, not compromise data integrity or trigger unintended actions.
From the tool's definition Tool name 'voice_status' and description 'Get current voice system status and pending voice input' indicate a read-only query operation that retrieves system state without modification.
Documented attack patterns abuse exactly the kind of access voice_status gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jarvis MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for voice_status:
{
"version": "1",
"default": "deny",
"tools": {
"voice_status": {}
}
}voice_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 current voice system status and pending voice input. It is categorised as a Read tool in the Jarvis MCP MCP Server, which means it retrieves data without modifying state.
Register the Jarvis MCP server in PolicyLayer and add a rule for voice_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 Jarvis MCP. Nothing to install.
voice_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 voice_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 voice_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.
voice_status is provided by the Jarvis MCP server (shantur/jarvis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Jarvis MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Jarvis MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.