AI agents call hardhat_verify 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 retrieves verification metadata and returns a file path—a read-only operation with no side effects. While it operates on a blockchain-enabled server, the specific tool itself performs data retrieval only, consistent with the Read category. The low severity reflects minimal security impact from an AI agent misusing a metadata lookup function.
From the tool's definition The tool description states it 'Returns build-info file path' and 'Get verification metadata', indicating it retrieves or queries data about contract verification without modifying or executing operations on the blockchain.
Attacks that exploit this kind of access
Get verification metadata for HashScan contract verification. Returns build-info file path. 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_verify: 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_verify 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_verify 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_verify. 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_verify 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 →