Scout leaderboard — top KOLs ranked by scout score, first-touch frequency, and swarm attraction rate (% of first-touched tokens that attract 3+ follow-on KOLs within 4h). ULTRA only.
AI agents call madeonsol_scout_leaderboard to retrieve information from Madeonsol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing KOL ranking data with no side effects, data modifications, code execution, or financial operations. It is purely a read operation that returns pre-computed or aggregated metrics. The 'ULTRA only' notation indicates access control but does not elevate the risk category from Read. Blast radius is minimal since the output is intelligence data only.
From the tool's definition Tool description indicates it retrieves and ranks KOL data by metrics (scout score, first-touch frequency, swarm attraction rate) with no modification or deletion mentioned. It is a leaderboard query returning analytical intelligence about Solana influencers.
Attacks that exploit this kind of access
Scout leaderboard — top KOLs ranked by scout score, first-touch frequency, and swarm attraction rate (% of first-touched tokens that attract 3+ follow-on KOLs within 4h). ULTRA only. It is categorised as a Read tool in the Madeonsol MCP Server, which means it retrieves data without modifying state.
Register the Madeonsol MCP server in PolicyLayer and add a rule for madeonsol_scout_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 Madeonsol. Nothing to install.
madeonsol_scout_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 madeonsol_scout_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 madeonsol_scout_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.
madeonsol_scout_leaderboard is provided by the Madeonsol MCP server (mcp-server-madeonsol). 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 →