AI agents call porkbun_domains to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation that queries domain inventory from a registrar account. However, the severity is elevated to 'medium' rather than 'low' because: (1) domain information can reveal infrastructure ownership and architecture; (2) expiration/auto-renew status could inform attack timing; (3) the Access server's self-hosted credential store means compromise here exposes the master token controlling all integrated…
From the tool's definition Tool returns 'all domains registered' with 'expiration dates and auto-renew status' — purely informational retrieval with no modification or side effects.
Attacks that exploit this kind of access
List all domains registered in the Porkbun account with their expiration dates and auto-renew status. Use this to audit domain ownership or find a specific domain. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for porkbun_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 Access. Nothing to install.
porkbun_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 porkbun_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 porkbun_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.
porkbun_domains is provided by the Access MCP server (scottpedia0/access). 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 →