AI agents use approve_liquidator_token to create or update resources in Justlend — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Justlend environment.
This tool approves token spending, which is a Write operation—it modifies the state of token allowances reversibly. While approval itself is not destructive, the high severity reflects that misconfiguration could enable unauthorized liquidation or fund transfers. The tool is contextual to financial activities (lending/liquidation) but the direct action is token authorization, not fund movement itself.
From the tool's definition Tool name 'approve_liquidator_token' and description 'Approve loan token spending for the Moolah public liquidator contract' indicate this creates or modifies token spending allowances on behalf of the user, a reversible authorization.
Attacks that exploit this kind of access
Approve loan token spending for the Moolah public liquidator contract. It is categorised as a Write tool in the Justlend MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Justlend MCP server in PolicyLayer and add a rule for approve_liquidator_token: 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.
approve_liquidator_token is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the approve_liquidator_token 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 approve_liquidator_token. 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.
approve_liquidator_token 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 →