Return all name clusters containing this form, sorted by bearer count.
AI agents call lookup to retrieve information from Name Variants without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The lookup tool queries a multilingual name romanization database and returns matching clusters sorted by bearer count. This is a passive read operation that retrieves existing data without creating, modifying, deleting, or executing anything. No side effects or irreversible actions are possible.
From the tool's definition Tool description states 'Return all name clusters containing this form' — a pure retrieval operation with no modification, deletion, or code execution. The verb 'Return' and the read-only nature of a lookup query confirm this is a data retrieval function.
Attacks that exploit this kind of access
Return all name clusters containing this form, sorted by bearer count. It is categorised as a Read tool in the Name Variants MCP Server, which means it retrieves data without modifying state.
Register the Name Variants MCP server in PolicyLayer and add a rule for lookup: 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 Name Variants. Nothing to install.
lookup 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 lookup 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 lookup. 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.
lookup is provided by the Name Variants MCP server (securityronin/name-variants). 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 →