get_yandex_direct_experiment
AI agents call get_yandex_direct_experiment 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.
Despite the empty description, the naming convention (get_*) and server context (Yandex Metrika analytics with retrieval-focused sibling tools) strongly suggest this retrieves experiment data rather than executing or modifying it. Confidence is reduced due to lack of explicit description, but the pattern is clear. No side effects are indicated by the tool family it belongs to.
From the tool's definition Tool name 'get_yandex_direct_experiment' uses the 'get_' prefix, consistent with sibling Read tools like 'get_account_info', 'get_browsers_report', 'get_content_analytics_*', and 'get_conversion_rate_by_source_and_landing'.
Attacks that exploit this kind of access
get_yandex_direct_experiment. 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 get_yandex_direct_experiment: 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.
get_yandex_direct_experiment 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_yandex_direct_experiment 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_yandex_direct_experiment. 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_yandex_direct_experiment 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 →