AI agents call hardhat_get_accounts 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 queries and returns account information and balances without creating, modifying, deleting, or executing any state-changing operations. It is a read-only operation that retrieves data from the blockchain. The low severity reflects that exposure of account balance information poses minimal direct risk, though it could be used for reconnaissance in a broader attack chain.
From the tool's definition Tool name 'hardhat_get_accounts' and description 'Get list of available accounts with balances' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get list of available accounts with balances. 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 hardhat_get_accounts: 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.
hardhat_get_accounts 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 hardhat_get_accounts 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 hardhat_get_accounts. 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.
hardhat_get_accounts 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 →