AI agents call get_mining_rewards to retrieve information from Justlend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves information about mining rewards from an API. It does not create, modify, delete, execute code, or commit financial transactions. The action is read-only: obtaining current reward status and APY metrics.
From the tool's definition Tool description states it 'Get[s] mining rewards' and 'Returns unclaimed rewards, mining APY, and reward breakdown from API' — purely data retrieval with no side effects or state changes.
Attacks that exploit this kind of access
Get mining rewards for supply markets (USDD, WBTC, etc.). Returns unclaimed rewards, mining APY, and reward breakdown from API. It is categorised as a Read tool in the Justlend MCP Server, which means it retrieves data without modifying state.
Register the Justlend MCP server in PolicyLayer and add a rule for get_mining_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 Justlend. Nothing to install.
get_mining_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_mining_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_mining_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_mining_rewards is provided by the Justlend MCP server (justlend/mcp-server-justlend). 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 →