compare_segments
AI agents call compare_segments 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.
This tool retrieves and compares analytics segments within Yandex Metrika, a read-only analytics platform. It queries existing data without side effects. The empty description reduces confidence slightly, but the naming convention and context of sibling tools strongly indicate a Read operation. Misuse would expose analytics data but pose minimal risk to the organization's systems.
From the tool's definition Tool name 'compare_segments' and sibling tools like 'compare_segments_drilldown', 'get_account_info', 'get_browsers_report', 'get_content_analytics_*', 'get_conversion_rate_*', and 'get_data_by_time' are all data retrieval operations.
Attacks that exploit this kind of access
compare_segments. 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: 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 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 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. 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 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 →