Get game-level context for an MLB game: starting pitchers (probable → confirmed), venue + park factor, hourly weather (wind speed/direction, temperature, precip probability) at first pitch, and lineup lock status. Returns a riskFlag of clean|low|medium|high for weather/park effects. Use BEFORE pl...
AI agents call mlb_game_context to retrieve information from PropProfessor MCP 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 game context data without creating, modifying, executing commands, or having financial impact on its own. While it's used in a betting/financial context (PropProfessor), the tool itself only reads and presents information to inform decisions—it does not move money, execute transactions, or modify any state. The riskFlag is a computed assessment, not a financial action.
From the tool's definition Tool retrieves and returns game-level context including starting pitchers, venue information, weather data, and lineup lock status. Uses verbs 'Get' and 'Returns' with no modification of data.
Attacks that exploit this kind of access
Get game-level context for an MLB game: starting pitchers (probable → confirmed), venue + park factor, hourly weather (wind speed/direction, temperature, precip probability) at first pitch, and lineup lock status. Returns a riskFlag of clean|low|medium|high for weather/park effects. Use BEFORE placing an MLB bet when the screen does not surface this. Automatically called by validate_play for league=. It is categorised as a Read tool in the PropProfessor MCP MCP Server, which means it retrieves data without modifying state.
Register the PropProfessor MCP server in PolicyLayer and add a rule for mlb_game_context: 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 PropProfessor MCP. Nothing to install.
mlb_game_context 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 mlb_game_context 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 mlb_game_context. 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.
mlb_game_context is provided by the PropProfessor MCP server (j17drake/propprofessor-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 →