Generate an answer grounded in web search results, with optional source restrictions (site/host/url).
AI agents call generative_search to retrieve information from Yandex Searchapi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and synthesizes information from existing web search results. It has no side effects on external systems, does not modify or delete data, and does not execute code or trigger external operations. It is a search and information retrieval function, placing it squarely in the Read category with low severity—an agent using this tool has minimal risk of causing harm.
From the tool's definition Tool description states it 'Generate[s] an answer grounded in web search results' with optional source restrictions.
Attacks that exploit this kind of access
Generate an answer grounded in web search results, with optional source restrictions (site/host/url). It is categorised as a Read tool in the Yandex Searchapi MCP Server, which means it retrieves data without modifying state.
Register the Yandex Searchapi MCP server in PolicyLayer and add a rule for generative_search: 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 Searchapi. Nothing to install.
generative_search 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 generative_search 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 generative_search. 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.
generative_search is provided by the Yandex Searchapi MCP server (shufl9dka/yandex-searchapi-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 →