Return only the highest-quality movement signals across requested leagues, ranked by signal strength. Each row includes movementGrade, riskScore (1-10), kaiCall (BET/CONSIDER/PASS), confidenceTier (TIER 1-4), consensusStrength (strong/moderate/weak/none), and a human-readable rationale string. Th...
AI agents call recommended_bets 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 is a data retrieval and analysis tool that queries betting signal information and returns ranked results. While it relates to sports betting context, it performs no financial transactions, does not execute bets, and does not modify any data. It solely retrieves and presents analytical information about market movements and signal quality.
From the tool's definition Tool returns rankings and quality ratings of betting signals with movement grades, risk scores, and confidence tiers.
Attacks that exploit this kind of access
Return only the highest-quality movement signals across requested leagues, ranked by signal strength. Each row includes movementGrade, riskScore (1-10), kaiCall (BET/CONSIDER/PASS), confidenceTier (TIER 1-4), consensusStrength (strong/moderate/weak/none), and a human-readable rationale string. The tier and kaiCall are quality ratings on the movement data (do sharp books really agree? is there a real line lag?), NOT predictions about which side will win. Generic market names (e.g. 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 recommended_bets: 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.
recommended_bets 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 recommended_bets 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 recommended_bets. 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.
recommended_bets 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 →