AI agents call fair_compute to retrieve information from Bet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs mathematical computation to derive probability estimates and fair odds. It reads/derives data but does not place bets, move money, or modify any state. It is an analytical/read-only tool used to inform betting decisions, not to execute them. Severity is low since misuse only produces incorrect probability outputs with no financial or destructive side effects.
From the tool's definition 'Calcola probabilità e quote fair (Poisson semplice)' — the tool computes/calculates probabilities and fair odds using a statistical model (simple Poisson distribution) for match outcomes (1X2, Over/Under 2.5, BTTS).
Attacks that exploit this kind of access
Calcola probabilità e quote fair (Poisson semplice) per 1X2 / OU 2.5 / BTTS. It is categorised as a Read tool in the Bet MCP Server, which means it retrieves data without modifying state.
Register the Bet MCP server in PolicyLayer and add a rule for fair_compute: 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 Bet. Nothing to install.
fair_compute 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 fair_compute 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 fair_compute. 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.
fair_compute is provided by the Bet MCP server (valerio357/bet_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 →