AI agents call mirror_get_transaction 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 retrieves transaction information from the Hedera blockchain mirror node. It performs a lookup by transaction ID and returns data (transfers, fees, result) without modifying, deleting, or executing any operations. The query-only nature with no state changes places it squarely in the Read category.
From the tool's definition Tool name 'mirror_get_transaction' and description 'Get single transaction details by transaction ID. Returns full transaction info including transfers, fees, and result.' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get single transaction details by transaction ID. Returns full transaction info including transfers, fees, and result. 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_transaction: 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_transaction 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_transaction 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_transaction. 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_transaction 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 →