reverse lookup: address to .eth name ONLY (does NOT work for .base.eth Basenames)
AI agents call get_name_for_address to retrieve information from BaseQL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely looks up and returns a name associated with a blockchain address. It is a read-only query with no ability to modify state, execute operations, or cause any destructive action. The blast radius of misuse is minimal — at worst, an agent could look up names for arbitrary addresses, which is publicly available blockchain data. Hence low severity.
From the tool's definition Tool performs a 'reverse lookup: address to .eth name ONLY' — a pure query operation that retrieves existing data with no modification, creation, or side effects.
Attacks that exploit this kind of access
reverse lookup: address to .eth name ONLY (does NOT work for .base.eth Basenames). It is categorised as a Read tool in the BaseQL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the BaseQL MCP Server MCP server in PolicyLayer and add a rule for get_name_for_address: 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 BaseQL MCP Server. Nothing to install.
get_name_for_address 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 get_name_for_address 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 get_name_for_address. 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.
get_name_for_address is provided by the BaseQL MCP Server MCP server (jnix2007/baseql-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 →