AI agents call get_moolah_liquidation_quote 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 retrieves liquidation pricing quotes for informational purposes. While it operates in a financial domain (lending/liquidation), it does not move money, execute liquidations, or modify any state - it only provides read-only estimates to inform decision-making. The caller must still approve and execute separate liquidation transactions.
From the tool's definition Tool name contains 'get' and description uses 'Estimate' - retrieves pricing information without creating side effects, modifying data, or executing transactions. The verb 'Estimate' indicates a query operation that returns calculated values.
Attacks that exploit this kind of access
Estimate the loan token cost to liquidate a position. 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_moolah_liquidation_quote: 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_moolah_liquidation_quote 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_moolah_liquidation_quote 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_moolah_liquidation_quote. 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_moolah_liquidation_quote 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 →