AI agents call get_toss_analysis 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 a local DuckDB database to retrieve pre-computed cricket analytics and statistics. It performs only data retrieval and analysis operations with no side effects, no state changes to the database, and no external operations. It is purely informational, making it a Read category tool with low severity risk.
From the tool's definition Tool name 'get_toss_analysis' and description indicate it retrieves and analyzes historical cricket statistics ('toss impact on outcomes', 'win % batting first vs chasing', 'toss winner win %', 'bat/field decision trends').
Attacks that exploit this kind of access
Does the toss matter at this venue / in this format? Toss impact on outcomes: win % batting first vs chasing, toss winner win %, and bat/field decision trends. 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_toss_analysis: 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_toss_analysis 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_toss_analysis 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_toss_analysis. 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_toss_analysis 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 →