AI agents call analytics.performance to retrieve information from Rekko MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates existing performance metrics without creating, modifying, deleting, or executing any operations. The action is read-only. Severity is low because even if an AI misuses this tool to retrieve performance data inappropriately, no financial transactions occur, no data is modified, and no external systems are triggered. The blast radius is confined to information disclosure.
From the tool's definition Tool performs 'Get aggregate trading performance statistics' — a retrieval operation that queries historical performance data (win rate, ROI, total P&L) with no side effects.
Attacks that exploit this kind of access
Get aggregate trading performance statistics — win rate, ROI, total P&L. It is categorised as a Read tool in the Rekko MCP MCP Server, which means it retrieves data without modifying state.
Register the Rekko MCP server in PolicyLayer and add a rule for analytics.performance: 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 Rekko MCP. Nothing to install.
analytics.performance 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 analytics.performance 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 analytics.performance. 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.
analytics.performance is provided by the Rekko MCP server (rekko-ai/rekko-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 →