Check ads.txt compliance for a publisher domain.
AI agents call check_ads_txt to retrieve information from Supply Ops Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and verifies compliance status of ads.txt records for a domain. It performs a query or audit function without creating, modifying, deleting, or executing any operations. The ads.txt file is a public record used for ad fraud prevention, and checking its compliance is a diagnostic read operation.
From the tool's definition Tool is named 'check_ads_txt' and described as checking 'ads.txt compliance for a publisher domain.' The verb 'check' and the compliance verification nature indicate a read-only diagnostic operation with no modification of data or systems.
Attacks that exploit this kind of access
Check ads.txt compliance for a publisher domain. It is categorised as a Read tool in the Supply Ops Agent MCP Server, which means it retrieves data without modifying state.
Register the Supply Ops Agent MCP server in PolicyLayer and add a rule for check_ads_txt: 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 Supply Ops Agent. Nothing to install.
check_ads_txt 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 check_ads_txt 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 check_ads_txt. 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.
check_ads_txt is provided by the Supply Ops Agent MCP server (mpessis/supply-ops-agent). 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 →