AI agents call search_domain to retrieve information from Wayback without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against archived data. It retrieves information about historical snapshots of websites but does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal—an agent could retrieve unwanted archived content but cannot damage data or systems.
From the tool's definition Tool 'search_domain' searches and retrieves archived URLs from the Internet Archive's Wayback Machine without modifying or deleting any data. The description states it finds archived URLs, which is a query/retrieval operation.
Attacks that exploit this kind of access
Find archived URLs under a domain or path prefix. Auto-detects matchType from input. It is categorised as a Read tool in the Wayback MCP Server, which means it retrieves data without modifying state.
Register the Wayback MCP server in PolicyLayer and add a rule for search_domain: 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 Wayback. Nothing to install.
search_domain 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 search_domain 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 search_domain. 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.
search_domain is provided by the Wayback MCP server (lakshyamehta03/wayback-machine-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 →