Get the play-by-play data for a specific game by its ID. The play-by-play data
AI agents call get_live_game_play_by_play to retrieve information from NBA MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches historical or current game event data without modifying, executing code, deleting, or moving money. It has no side effects beyond returning query results. It falls squarely into the Read category with low risk and high confidence.
From the tool's definition Tool retrieves 'play-by-play data for a specific game by its ID' — a data query operation. The server description states it 'enables LLMs to retrieve NBA data'.
Attacks that exploit this kind of access
Get the play-by-play data for a specific game by its ID. The play-by-play data. It is categorised as a Read tool in the NBA MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NBA MCP Server MCP server in PolicyLayer and add a rule for get_live_game_play_by_play: 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 MCP Server. Nothing to install.
get_live_game_play_by_play 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 get_live_game_play_by_play 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 get_live_game_play_by_play. 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.
get_live_game_play_by_play is provided by the NBA MCP Server MCP server (stevenyuser/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 →