AI agents call nba_live_boxscore 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 NBA game box score data based on a game ID. It performs a read-only query operation with no side effects, no code execution, no data modification, and no financial impact. The server itself is marked as providing read-only access to public sports data, making this a straightforward data retrieval operation.
From the tool's definition Tool description explicitly states 'Get the live box score' and server description confirms 'read-only tools to query live scores, box scores' with 'no side effects'. The tool retrieves data from cdn.nba.com without modification or execution capabilities.
Attacks that exploit this kind of access
Get the live box score for a 10-digit NBA game id from cdn.nba.com. 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_live_boxscore: 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_live_boxscore 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_live_boxscore 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_live_boxscore. 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_live_boxscore 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 →