AI agents call get_market_data 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 queries and returns financial market information without modifying any data or executing transactions. It has no capability to transfer assets, change balances, or perform irreversible actions. The blast radius of misuse is minimal—an agent could only retrieve information that would otherwise be publicly available on-chain.
From the tool's definition Tool name 'get_market_data' and description explicitly states it retrieves 'detailed market data' including 'supply/borrow APY, TVL, utilization' with no mention of state changes, transactions, or side effects.
Attacks that exploit this kind of access
Get detailed market data for a specific JustLend market: supply/borrow APY, TVL, utilization,. 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_market_data: 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_market_data 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_market_data 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_market_data. 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_market_data 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 →