Get play-by-play information for a specific game.
AI agents call get_play_by_play to retrieve information from NHL MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical or live game play-by-play data from the NHL API. It performs no modifications, deletions, or external operations—only data query and retrieval. The blast radius of misuse is minimal (information disclosure at most). It aligns with sibling tools like get_daily_scores_by_date and get_game_boxscore, all of which are read operations.
From the tool's definition Tool name 'get_play_by_play' and description 'Get play-by-play information for a specific game' indicate a retrieval operation.
Attacks that exploit this kind of access
Get play-by-play information for a specific game. It is categorised as a Read tool in the NHL MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NHL MCP Server MCP server in PolicyLayer and add a rule for get_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 NHL MCP Server. Nothing to install.
get_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_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_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_play_by_play is provided by the NHL MCP Server MCP server (sanchorelaxo/mcp-server-sandbox). 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 →