AI agents call addressbook_list to retrieve information from HashPilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries stored address book data without modifying, executing, deleting, or causing financial transactions. The explicit clarification that private keys are not returned further reduces risk. The blast radius of misuse is minimal—an agent could only enumerate stored account information already accessible to the user.
From the tool's definition Tool name 'addressbook_list' and description 'List all accounts stored in the address book. Returns account IDs, aliases, nicknames, and metadata (but not private keys).' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all accounts stored in the address book. Returns account IDs, aliases, nicknames, and metadata (but not private keys). It is categorised as a Read tool in the HashPilot MCP Server, which means it retrieves data without modifying state.
Register the HashPilot MCP server in PolicyLayer and add a rule for addressbook_list: 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 HashPilot. Nothing to install.
addressbook_list 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 addressbook_list 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 addressbook_list. 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.
addressbook_list is provided by the HashPilot MCP server (justmert/hashpilot). 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 →