AI agents call sports.nfl-games to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available NFL game data (schedules, scores, venues) without modifying, executing, or deleting anything. It is a straightforward read-only query operation. The pay-per-call settlement mechanism via x402 does not change the tool's operational category—payment is handled separately from the tool's function. No blast radius from misuse beyond potentially wasted API calls.
From the tool's definition Tool returns 'schedule + scores' and 'status, scores, venue' — purely informational queries with no mutation or execution.
Attacks that exploit this kind of access
NFL games (schedule + scores) by season, week, or team — status, scores, venue. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for sports.nfl-games: 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 Mcp. Nothing to install.
sports.nfl-games 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 sports.nfl-games 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 sports.nfl-games. 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.
sports.nfl-games is provided by the MCP server (@2sio/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 →