Fetch F1 drivers. Optionally filter by driver number.
AI agents call list_drivers to retrieve information from OpenF1 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 or queries driver information from the OpenF1 API without any side effects, modifications, or irreversible actions. It aligns with the Read category definition of retrieving data. The severity is low because misuse would only expose already-public F1 driver roster information with no operational impact.
From the tool's definition Tool name 'list_drivers' with description 'Fetch F1 drivers' indicates data retrieval. The optional filter parameter (driver number) allows querying but does not modify, delete, or execute operations.
Attacks that exploit this kind of access
Fetch F1 drivers. Optionally filter by driver number. It is categorised as a Read tool in the OpenF1 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenF1 MCP Server MCP server in PolicyLayer and add a rule for list_drivers: 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 OpenF1 MCP Server. Nothing to install.
list_drivers 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 list_drivers 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 list_drivers. 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.
list_drivers is provided by the OpenF1 MCP Server MCP server (jimmyjoe009/openf1_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 →