AI agents call get_style_matchup to retrieve information from Cricket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries historical cricket statistics to analyze player performance patterns. It retrieves and analyzes existing data from the DuckDB database with no side effects, no code execution, no data modification, and no destructive operations. It is a pure read operation that provides analytical insights.
From the tool's definition Tool name 'get_style_matchup' and description indicate it 'breaks down a batter' performance metrics against different bowling styles.
Attacks that exploit this kind of access
How does this player perform against pace vs spin / left-handers vs right-handers? Breaks down a batter. It is categorised as a Read tool in the Cricket MCP Server, which means it retrieves data without modifying state.
Register the Cricket MCP server in PolicyLayer and add a rule for get_style_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 Cricket. Nothing to install.
get_style_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 get_style_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 get_style_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.
get_style_matchup is provided by the Cricket MCP server (mavaali/cricket-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 →