Analyze different types of traffic sources (organic, direct, referral).
AI agents call get_traffic_sources_types 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 analyzes traffic source metrics from Yandex Metrika analytics. It performs no data modification, deletion, code execution, or financial transactions. It is a straightforward analytics query that returns traffic classification data, which is characteristic of Read operations.
From the tool's definition Tool name 'get_traffic_sources_types' and description 'Analyze different types of traffic sources' indicate data retrieval. The verb 'get' and 'analyze' are read operations that query analytics data without modification or side effects.
Attacks that exploit this kind of access
Analyze different types of traffic sources (organic, direct, referral). 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_traffic_sources_types: 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_traffic_sources_types 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_traffic_sources_types 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_traffic_sources_types. 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_traffic_sources_types 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 →