Analyze a screenlog session into a deterministic activity report: time-by-app (most first), active vs idle, top window titles, hourly histogram. This is how you answer 'what did this machine / person spend the most time on'. Returns structured numbers + a runner-ready narrativePrompt for prose. N...
AI agents call screenlog_analyze to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | |
idle_gap_sec | integer | — | a gap larger than this with no kept frame counts as idle (default 120) |
max_attribute_sec | integer | — | max time one frame may represent (default interval×4) |
Parameters from the server's own tool schema.
Even though screenlog_analyze only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Analyze a screenlog session into a deterministic activity report: time-by-app (most first), active vs idle, top window titles, hourly histogram. This is how you answer 'what did this machine / person spend the most time on'. Returns structured numbers + a runner-ready narrativePrompt for prose. No LLM needed for the breakdown — the numbers are exact. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
screenlog_analyze accepts 3 parameters: id, idle_gap_sec, max_attribute_sec. Required: id. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for screenlog_analyze: 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 Yaver. Nothing to install.
screenlog_analyze 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 screenlog_analyze 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 screenlog_analyze. 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.
screenlog_analyze is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.