AI agents use approve_underlying 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 creates or modifies token allowances—a reversible Write action that enables future transfers of user assets. While not immediately destructive, it carries high severity because approving excessive token spending could lead to unauthorized fund transfers if the jToken contract is compromised or if an AI agent grants unchecked approvals.
From the tool's definition Tool name 'approve_underlying' and description 'Approve the jToken contract to spend your underlying TRC20 tokens' indicate this grants spending permissions on user tokens via smart contract approval, a reversible but critical authorization action.
Attacks that exploit this kind of access
Approve the jToken contract to spend your underlying TRC20 tokens. 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_underlying: 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_underlying 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_underlying 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_underlying. 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_underlying 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 →