AI agents call mirror_get_account_rewards 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 historical staking reward information for a blockchain account. It is a read-only query operation with no side effects—it does not modify state, execute code, delete data, or move funds. The 'Get' verb and passive voice ('Returns') confirm data retrieval with zero destructive or transactional impact.
From the tool's definition Tool performs a 'Get' operation on staking reward history with no modification capability. The description states it 'Returns rewards earned' (retrieval only), with no create, update, delete, or execution capabilities described.
Attacks that exploit this kind of access
Get staking reward history for an account. Returns rewards earned per staking period. 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_account_rewards: 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_account_rewards 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_account_rewards 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_account_rewards. 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_account_rewards 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 →