AI agents call get_fielding_stats 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 fielding statistics from a DuckDB database without creating, modifying, deleting, or executing any operations. It performs aggregations and filtering on existing ball-by-ball data to return fielding metrics. No side effects or irreversible changes are possible.
From the tool's definition Tool name 'get_fielding_stats' and description indicate data retrieval only: 'Who are the best fielders? How many catches has a player taken? Fielding stats from ball-by-ball data: catches, run outs, stumpings, total dismissals.' These are all query/read…
Attacks that exploit this kind of access
Who are the best fielders? How many catches has a player taken? Fielding stats from ball-by-ball data: catches, run outs, stumpings, total dismissals. 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_fielding_stats: 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_fielding_stats 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_fielding_stats 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_fielding_stats. 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_fielding_stats 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 →