Get recent parlay recommendations generated by the system
AI agents call get_parlay_history to retrieve information from Fantasy MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves past parlay recommendations—a read-only operation with no side effects. While the Fantasy MCP server deals with financial betting domain (parlay recommendations are financial predictions), this specific tool does not move money, create new financial obligations, or execute trades. It simply fetches stored historical data.
From the tool's definition Tool name 'get_parlay_history' and description 'Get recent parlay recommendations generated by the system' indicate retrieval of historical data without modification or execution of transactions.
Attacks that exploit this kind of access
Get recent parlay recommendations generated by the system. It is categorised as a Read tool in the Fantasy MCP MCP Server, which means it retrieves data without modifying state.
Register the Fantasy MCP server in PolicyLayer and add a rule for get_parlay_history: 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 Fantasy MCP. Nothing to install.
get_parlay_history 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_parlay_history 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_parlay_history. 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_parlay_history is provided by the Fantasy MCP server (mattarm/fantasy_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 →