팀의 최근 N경기 — 결과 + 실제 타순(타순/포지션/선수) + 선발투수.
AI agents call game_log to retrieve information from Kaist Beast Baseball without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and displays historical baseball game data including results, batting lineups, and pitcher information. It performs read-only retrieval operations without creating, modifying, deleting, or executing external actions. This is a classic Read operation with minimal security risk in the context of a baseball analytics system.
From the tool's definition Tool name 'game_log' and description indicate retrieval of historical game data: '팀의 최근 N경기 — 결과 + 실제 타순(타순/포지션/선수) + 선발투수' translates to 'team's recent N games — results + actual batting order (batting order/position/player) + starting pitcher.' This…
Attacks that exploit this kind of access
팀의 최근 N경기 — 결과 + 실제 타순(타순/포지션/선수) + 선발투수. It is categorised as a Read tool in the Kaist Beast Baseball MCP Server, which means it retrieves data without modifying state.
Register the Kaist Beast Baseball MCP server in PolicyLayer and add a rule for game_log: 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 Kaist Beast Baseball. Nothing to install.
game_log 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 game_log 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 game_log. 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.
game_log is provided by the Kaist Beast Baseball MCP server (mw-jeong/kaist-beast-baseball-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 →