validate_play · PropProfessor MCP: Risk & Policy

WHAT IT DOES

What validate_play does on PropProfessor MCP

AI agents invoke validate_play to trigger actions in PropProfessor MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why validate_play needs a policy

This tool orchestrates multiple external operations (fetching live data, running context checks, querying books) and produces a betting decision verdict. It triggers a chain of external calls and actions whose effects depend on arguments. While it does not itself place a bet, it is the final decision gate before betting, making misuse high severity.

From the tool's definition 'Run all validation checks', 're-fetch the latest screen data', 'run player_context for injury/news', 'check execution quality on the requested book', 'return a single verdict (BET / CONSIDER / PASS)'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

validate_play Rate-limited

validate_play stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "validate_play": {
      "limits": [
        {
          "counter": "validate_play_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches PropProfessor MCP, so you can run agents against it safely.

FAQ

Questions about validate_play

What does the validate_play tool do? +

Run all validation checks on a specific play in one call: re-fetch the latest screen data for the game, run player_context for injury/news, check execution quality on the requested book, and return a single verdict (BET / CONSIDER / PASS) with all supporting evidence. Use this after a screen_ranked or recommended_bets result to confirm a specific play before placing the bet. Pass. It is categorised as a Execute tool in the PropProfessor MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on validate_play? +

Register the PropProfessor MCP server in PolicyLayer and add a rule for validate_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 PropProfessor MCP. Nothing to install.

What risk level is validate_play? +

validate_play is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit validate_play? +

Yes. Add a rate_limit block to the validate_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.

How do I block validate_play completely? +

Set action: deny in the PolicyLayer policy for validate_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.

What MCP server provides validate_play? +

validate_play 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.