AI agents call value_detect 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 is a read-only analytical tool that queries and compares betting odds data to identify betting opportunities. While it operates in a financial domain (football betting), it does not execute bets, move money, or commit financial obligations—it merely surfaces information to support decision-making. The user retains full control over whether to act on the recommendations.
From the tool's definition Tool performs analysis comparing market odds (quote mercato) versus fair odds (fair) to detect value opportunities (value pick) with an edge threshold.
Attacks that exploit this kind of access
Confronta quote mercato vs fair per trovare fino a 3 value pick (edge >= 5%). 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 value_detect: 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.
value_detect 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 value_detect 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 value_detect. 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.
value_detect 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 →