Time per device for users who run Vetroscope across multiple machines (or paired with the browser extension). Each device reports total active / passive seconds, days active, first/last seen, and most-frequent platform. The user
AI agents call get_device_breakdown to retrieve information from Vetroscope MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries time-tracking metrics from a local SQLite database without any capability to modify, execute commands, or cause side effects. It is a straightforward data retrieval operation consistent with the 'Read' category. The data is sensitive (personal time-tracking) but the risk is limited to information disclosure rather than misuse through modification or execution.
From the tool's definition Tool name 'get_device_breakdown' and description explicitly state it retrieves time-tracking data 'per device' including 'total active/passive seconds, days active, first/last seen, and most-frequent platform.' The server itself is described as 'read-only'…
Attacks that exploit this kind of access
Time per device for users who run Vetroscope across multiple machines (or paired with the browser extension). Each device reports total active / passive seconds, days active, first/last seen, and most-frequent platform. The user. It is categorised as a Read tool in the Vetroscope MCP MCP Server, which means it retrieves data without modifying state.
Register the Vetroscope MCP server in PolicyLayer and add a rule for get_device_breakdown: 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 Vetroscope MCP. Nothing to install.
get_device_breakdown 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_device_breakdown 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_device_breakdown. 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_device_breakdown is provided by the Vetroscope MCP server (rankin-works/vetroscope-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 →