AI agents call get_goalie_stats to retrieve information from Swehockey without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves aggregated goalie statistics data from a public sports database. It has no side effects, cannot modify data, and presents minimal security risk. The operation is informational only, consistent with other sibling tools (get_player_stats, get_schedule, get_standings) that all perform data lookups without mutations.
From the tool's definition Tool description states it retrieves 'Goalie stats from the complete rosters, aggregated and grouped by club' — a pure data retrieval operation with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Goalie stats from the complete rosters, aggregated and grouped by club. It is categorised as a Read tool in the Swehockey MCP Server, which means it retrieves data without modifying state.
Register the Swehockey MCP server in PolicyLayer and add a rule for get_goalie_stats: 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 Swehockey. Nothing to install.
get_goalie_stats 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_goalie_stats 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_goalie_stats. 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_goalie_stats is provided by the Swehockey MCP server (troelskn/swehockey). 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 →