AI agents call get_rewards to retrieve information from Refinore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries blockchain state to display wallet rewards without side effects. It is a read-only operation that poses minimal risk — misuse would only expose the user's own reward data, not authorize fund transfers or execute transactions. Severity is low because reading account balances carries negligible blast radius.
From the tool's definition Tool name 'get_rewards' and description 'Get unclaimed rewards' — retrieves wallet reward data with no modification, deletion, or execution of transactions. Returns informational data: 'unclaimed SOL, unrefined ORE, and bonus ORE'.
Attacks that exploit this kind of access
Get unclaimed rewards for a wallet — includes unclaimed SOL, unrefined ORE, and bonus ORE. It is categorised as a Read tool in the Refinore MCP Server, which means it retrieves data without modifying state.
Register the Refinore MCP server in PolicyLayer and add a rule for get_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 Refinore. Nothing to install.
get_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 get_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 get_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.
get_rewards is provided by the Refinore MCP server (jusscubs/refinore-mcp). 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 →