Get actual search queries typed by users. Use to find negative keywords or analyze traffic quality.
AI agents call get_search_queries to retrieve information from Yandex Direct without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
date_to | string | Yes | End date YYYY-MM-DD |
api_token | string | Yes | CRITICAL: Always pass API_TOKEN here. |
date_from | string | Yes | Start date YYYY-MM-DD |
campaign_ids | array | — | Optional: Filter by specific Campaign IDs. |
client_login | string | — | CRITICAL: Always pass CLIENT_LOGIN here if it exists in system prompt. |
Parameters from the server's own tool schema.
This tool retrieves search query data for analysis purposes. While it accesses user behavior data (which may be sensitive), it performs only read operations without side effects. The moderate severity reflects the sensitive nature of user search data, but the low risk of misuse compared to write, execute, or destructive operations.
From the tool's definition Tool name: 'get_search_queries'. Description: 'Get actual search queries typed by users. Use to find negative keywords or analyze traffic quality.' The verb 'Get' and use cases 'find' and 'analyze' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Get actual search queries typed by users. Use to find negative keywords or analyze traffic quality. It is categorised as a Read tool in the Yandex Direct MCP Server, which means it retrieves data without modifying state.
get_search_queries accepts 5 parameters: date_to, api_token, date_from, campaign_ids, client_login. Required: date_to, api_token, date_from. The full parameter table on this page comes from the server's own tool schema.
Register the Yandex Direct MCP server in PolicyLayer and add a rule for get_search_queries: 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 Yandex Direct. Nothing to install.
get_search_queries 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_search_queries 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_search_queries. 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_search_queries is provided by the Yandex Direct MCP server (yandex-direct-mcp-server). 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 →