AI agents call get_leaderboard to retrieve information from Axie without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries leaderboard data without creating, modifying, deleting, or executing any operations. It returns competitive ranking information, which is a standard read operation. The blast radius of misuse is minimal—an agent could only retrieve publicly available ranking data, posing no security, financial, or destructive risk.
From the tool's definition Tool name 'get_leaderboard' and description 'Get leaderboard rankings for various competitive categories' indicate a retrieval operation.
Attacks that exploit this kind of access
Get leaderboard rankings for various competitive categories in Axie Infinity. It is categorised as a Read tool in the Axie MCP Server, which means it retrieves data without modifying state.
Register the Axie MCP server in PolicyLayer and add a rule for get_leaderboard: 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 Axie. Nothing to install.
get_leaderboard 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_leaderboard 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_leaderboard. 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_leaderboard is provided by the Axie MCP server (jackdlogan/axie-mcp). 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 →