AI agents call semrush_keyword_ads_history to retrieve information from Semrush without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries historical advertising data (domains that bid on keywords) without creating, modifying, deleting, or executing any operations. It is purely informational retrieval of Semrush's analytics data. The cost metric (100 API units) reflects the data volume accessed, not the severity of the action. No side effects or irreversible changes are possible.
From the tool's definition Tool description states 'Get domains that bid on a keyword in the last 12 months' — a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Get domains that bid on a keyword in the last 12 months (100 API units per line). It is categorised as a Read tool in the Semrush MCP Server, which means it retrieves data without modifying state.
Register the Semrush MCP server in PolicyLayer and add a rule for semrush_keyword_ads_history: 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 Semrush. Nothing to install.
semrush_keyword_ads_history 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 semrush_keyword_ads_history 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 semrush_keyword_ads_history. 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.
semrush_keyword_ads_history is provided by the Semrush MCP server (superseoworld/semrush-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 →