AI agents call get_what_if 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 retrieves or computes analytical/predictive data about cricket players without modifying the database or executing external code. It performs a read operation on existing cricket delivery data to answer 'what-if' questions. While the description is truncated, the context of a cricket analytics server with statistical query tools strongly indicates this is a Read-category operation.
From the tool's definition Tool name 'get_what_if' and description fragment 'What would this player' indicate a query/analysis tool. Sibling tools (get_batting_records, get_bowling_records, get_career_impact, etc.) are all Read operations querying cricket statistics from a local DuckDB…
Attacks that exploit this kind of access
What would this player\\. 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_what_if: 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_what_if 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_what_if 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_what_if. 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_what_if 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 →