AI agents call mirror_get_nft 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 existing blockchain data (NFT metadata, ownership, timestamps) without creating, modifying, deleting, or executing any transactions. It is a passive information lookup against a blockchain mirror/indexer, characteristic of a Read category tool. The low severity reflects minimal blast radius — querying public blockchain data cannot cause financial loss or data destruction.
From the tool's definition Tool name 'mirror_get_nft' and description 'Get single NFT info' indicates a retrieval operation. The description explicitly states it 'Returns metadata, current owner, and creation timestamp' — read-only queries with no side effects.
Attacks that exploit this kind of access
Get single NFT info by serial number. Returns metadata, current owner, and creation timestamp. 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 mirror_get_nft: 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.
mirror_get_nft 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 mirror_get_nft 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 mirror_get_nft. 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.
mirror_get_nft 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 →