Find game_id by team matchup and optional date. Accepts team names.
AI agents call find_game to retrieve information from Nba Stats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (game identifiers) based on input parameters (team names and optional date). It has no side effects, does not execute code or external operations, does not modify data, and does not involve financial transactions. It is a pure read operation that returns metadata to support downstream queries.
From the tool's definition Tool 'find_game' accepts team names and returns a game_id—a lookup/retrieval operation with no modification or execution capability. The description states it 'Find[s] game_id', indicating a query operation.
Documented attack patterns abuse exactly the kind of access find_game gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nba Stats, and nothing reaches the server without passing your rules. This is the rule we recommend for find_game:
{
"version": "1",
"default": "deny",
"tools": {
"find_game": {}
}
}find_game is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find game_id by team matchup and optional date. Accepts team names. It is categorised as a Read tool in the Nba Stats MCP Server, which means it retrieves data without modifying state.
Register the Nba Stats MCP server in PolicyLayer and add a rule for find_game: 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 Stats. Nothing to install.
find_game 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 find_game 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 find_game. 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.
find_game is provided by the Nba Stats MCP server (labeveryday/nba-stats-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nba Stats, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Nba Stats tools catalogued and risk-classified — across an index of 43,000+ MCP servers.