AI agents use approve_jst_for_voting 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 a spender (WJST voting contract) to transfer JST tokens on behalf of the caller. Token approvals are Write operations—they create or modify authorization state reversibly. While the caller can later revoke or adjust the approval, misuse could allow an AI agent to grant excessive allowance to a contract, leading to unintended token transfers or loss of funds.
From the tool's definition approve_jst_for_voting - Approve JST token for the WJST voting contract. This is a token approval operation that modifies allowance state on the TRON blockchain.
Attacks that exploit this kind of access
Approve JST token for the WJST voting contract. Required before depositing JST to get voting power. 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_jst_for_voting: 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_jst_for_voting 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_jst_for_voting 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_jst_for_voting. 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_jst_for_voting 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 →