This endpoint provides aggregated LLM mentions metrics grouped by the most frequently mentioned domains for the specified target
AI agents call ai_opt_llm_ment_top_domains to retrieve information from Dataforseo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
target | array | Yes | Array of target objects to search for LLM mentions. Each object must contain either 'domain' or 'keyword'. Maximum number of targets: 1000 |
platform | string | — | Platform to search for LLM mentions |
links_scope | string | — | specifies which links will be used to extract domains and aggregation |
language_code | string | — | Search engine language code (e.g., 'en') |
location_name | string | — | full name of the location, example: 'United Kingdom', 'United States' |
items_list_limit | number | — | maximum number of results in the items array, min value is 1, max value is 10 |
internal_list_limit | number | — | maximum number of elements within internal arrays, min value is 1, max value is 10 |
initial_dataset_filters | array | — | Array-based filter expression. A single condition is a 3-element array: [field, operator, value]. Combine conditions with ["and"|"or"] between them: [condition, |
Parameters from the server's own tool schema.
This is a query/retrieval operation that fetches and aggregates existing metrics about domain mentions in LLM contexts. There are no side effects, no data creation, modification, or deletion, and no code execution. The tool is read-only, making it the lowest risk category.
From the tool's definition The tool provides aggregated LLM mentions metrics grouped by domains—it 'provides' and retrieves data with no modification capability. The description uses passive language ('provides...grouped by') indicating data retrieval only.
Attacks that exploit this kind of access
This endpoint provides aggregated LLM mentions metrics grouped by the most frequently mentioned domains for the specified target. It is categorised as a Read tool in the Dataforseo MCP Server, which means it retrieves data without modifying state.
ai_opt_llm_ment_top_domains accepts 8 parameters: target, platform, links_scope, language_code, location_name, items_list_limit, internal_list_limit, initial_dataset_filters. Required: target. The full parameter table on this page comes from the server's own tool schema.
Register the Dataforseo MCP server in PolicyLayer and add a rule for ai_opt_llm_ment_top_domains: 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 Dataforseo. Nothing to install.
ai_opt_llm_ment_top_domains 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 ai_opt_llm_ment_top_domains 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 ai_opt_llm_ment_top_domains. 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.
ai_opt_llm_ment_top_domains is provided by the Dataforseo MCP server (dataforseo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.