Execute transfers using player names. IRREVERSIBLE.
AI agents call make_transfers to permanently remove resources in FPL MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although 'transfers' in fantasy sports are technically reversible through counter-transfers in subsequent gameweeks, the tool explicitly labels itself as IRREVERSIBLE, indicating that the immediate action cannot be undone. This constitutes a destructive operation that irreversibly alters the user's team state.
From the tool's definition Tool description explicitly states 'Execute transfers' and 'IRREVERSIBLE'. The FPL API context confirms this modifies team composition in a Fantasy Premier League account in a way that cannot be undone.
Attacks that exploit this kind of access
Execute transfers using player names. IRREVERSIBLE. It is categorised as a Destructive tool in the FPL MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the FPL MCP Server MCP server in PolicyLayer and add a rule for make_transfers: 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 FPL MCP Server. Nothing to install.
make_transfers is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the make_transfers 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 make_transfers. 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.
make_transfers is provided by the FPL MCP Server MCP server (lewis-king/fpl-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 →