AI agents call nba_team_game_log to retrieve information from Nba without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves statistical data about past or current games for a team. It performs a query operation with no side effects, no data modification, and no execution of external commands. It fits the Read category: retrieves or queries data with no side effects. Low severity due to the benign nature of publicly available sports statistics.
From the tool's definition Tool description explicitly states 'Get game-by-game statistics' and server is described as 'read-only tools to query live scores, box scores, player info, standings, and more'. Tool retrieves historical or current game data with no modification capabilities.
Attacks that exploit this kind of access
Get game-by-game statistics for an NBA team in a season. It is categorised as a Read tool in the Nba MCP Server, which means it retrieves data without modifying state.
Register the Nba MCP server in PolicyLayer and add a rule for nba_team_game_log: 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 Nba. Nothing to install.
nba_team_game_log 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 nba_team_game_log 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 nba_team_game_log. 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.
nba_team_game_log is provided by the Nba MCP server (ufo2243/nba-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 →