View the top-performing agents ranked by P&L, wins, or total bets.
AI agents call leaderboard to retrieve information from ProfitPlay MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays leaderboard rankings based on performance metrics. It is a read-only operation that queries existing data about agent performance. There is no data modification, deletion, code execution, or financial transaction involved.
From the tool's definition Tool description states 'View the top-performing agents ranked by P&L, wins, or total bets.' The verb 'View' and action of ranking/displaying existing leaderboard data indicates retrieval of information without modification or side effects.
Attacks that exploit this kind of access
View the top-performing agents ranked by P&L, wins, or total bets. It is categorised as a Read tool in the ProfitPlay MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ProfitPlay MCP Server MCP server in PolicyLayer and add a rule for 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 ProfitPlay MCP Server. Nothing to install.
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 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 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.
leaderboard is provided by the ProfitPlay MCP Server MCP server (jarvismaximum-hue/profitplay-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 →