Analyze how a player performs against specific opponents
AI agents call analyze_matchup 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 aggregates performance data to generate insights. It has no side effects: it does not execute trades, place bets, modify data, delete records, or trigger external operations. Even in the context of a betting optimization system, analysis of matchup statistics is purely informational.
From the tool's definition Tool description states it 'Analyze[s] how a player performs' — a retrieval and analysis action with no modification or execution of external systems. The word 'analyze' indicates data querying and computation over historical/statistical information.
Attacks that exploit this kind of access
Analyze how a player performs against specific opponents. 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 analyze_matchup: 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.
analyze_matchup 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 analyze_matchup 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 analyze_matchup. 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.
analyze_matchup 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 →