AI agents call get_head_to_head 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 (win/loss records between teams) from a DuckDB database and returns read-only aggregated results. It has no side effects, does not modify data, does not execute code or commands, and does not involve financial transactions. The blast radius of misuse is minimal—an AI agent could only retrieve comparative team statistics, which is harmless.
From the tool's definition Tool name 'get_head_to_head' and description 'Returns total matches, wins for each side, draws, ties, and no results' indicate pure data retrieval with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
What is the win/loss record between two teams? Returns total matches, wins for each side, draws, ties, and no results. 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_head_to_head: 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_head_to_head 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_head_to_head 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_head_to_head. 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_head_to_head 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 →