compare_segments_drilldown
AI agents call compare_segments_drilldown to retrieve information from Ya Metrics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to compare user segments and drill down into analytical data from Yandex Metrika. Despite the empty description, the context indicates this performs read-only analytics queries that retrieve and compare existing data without modifying or deleting anything.
From the tool's definition Tool name contains 'compare_segments_drilldown' and is part of a Yandex Metrika analytics server for accessing 'traffic, content, demographics, conversion, e-commerce, and drill-down reports.' The name strongly suggests data comparison and drill-down analysis…
Attacks that exploit this kind of access
compare_segments_drilldown. It is categorised as a Read tool in the Ya Metrics MCP Server, which means it retrieves data without modifying state.
Register the Ya Metrics MCP server in PolicyLayer and add a rule for compare_segments_drilldown: 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 Ya Metrics. Nothing to install.
compare_segments_drilldown 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 compare_segments_drilldown 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 compare_segments_drilldown. 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.
compare_segments_drilldown is provided by the Ya Metrics MCP server (mrkhachaturov/ya-metrics-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 →