AI agents call fpl_bootstrap to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches public Fantasy Premier League reference data used to initialize client applications. The bootstrap pattern provides read-only access to game state snapshots—players' metadata, team information, fixtures—with no side effects, no data modification, and no code execution. Severity is low because misuse would merely return redundant data already public in the game.
From the tool's definition Tool name contains 'Get' action and description explicitly states 'Get Fantasy Premier League bootstrap data', which retrieves immutable public game data (players, teams, etc.) without modifying or executing anything.
Attacks that exploit this kind of access
Get Fantasy Premier League bootstrap data (players, teams, etc.). It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
Register the UnClick MCP server in PolicyLayer and add a rule for fpl_bootstrap: 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 UnClick. Nothing to install.
fpl_bootstrap 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 fpl_bootstrap 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 fpl_bootstrap. 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.
fpl_bootstrap is provided by the UnClick MCP server (@unclick/mcp-server). 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 →