AI agents call get_race_lead_changes to retrieve information from F1 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 existing race analytics data (lead changes, lap numbers, leader identifiers) for analysis purposes. It performs no write, deletion, execution, or financial operations. The verb 'Get' and the read-only nature of historical race telemetry data classify this clearly as a Read operation with low severity.
From the tool's definition Tool name 'get_race_lead_changes' and description 'Get all lead changes during the race with lap and new leader' indicate retrieval of historical race data with no modification or side effects.
Attacks that exploit this kind of access
Get all lead changes during the race with lap and new leader. It is categorised as a Read tool in the F1 MCP Server, which means it retrieves data without modifying state.
Register the F1 MCP server in PolicyLayer and add a rule for get_race_lead_changes: 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 F1. Nothing to install.
get_race_lead_changes 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_race_lead_changes 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_race_lead_changes. 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_race_lead_changes is provided by the F1 MCP server (luffy610/f1-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 →