Get betting odds for a specific event from selected bookmakers.
AI agents call get_odds to retrieve information from Odds-API MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves sports betting odds data from bookmakers. It queries and returns information about odds for a specific event without creating, modifying, deleting, executing code, or committing financial transactions. While the data is used for betting decisions, the tool itself performs only a read operation.
From the tool's definition Tool name 'get_odds' and description 'Get betting odds for a specific event from selected bookmakers' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get betting odds for a specific event from selected bookmakers. It is categorised as a Read tool in the Odds-API MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Odds-API MCP Server MCP server in PolicyLayer and add a rule for get_odds: 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 Odds-API MCP Server. Nothing to install.
get_odds 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 get_odds 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 get_odds. 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.
get_odds is provided by the Odds-API MCP Server MCP server (odds-api-io/odds-api-mcp-server). 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 →