AI agents call check_rules to retrieve information from Tru without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays configuration data about spending rules and permissions without creating, modifying, deleting, executing code, or moving money. It is a query/read operation that returns existing state information to the user. The low severity reflects minimal blast radius—misuse would only expose the user's own rule configuration, not cause financial harm or destructive changes.
From the tool's definition Tool description states 'List your current app rules' and 'Shows spending limits, action permissions, and escalation thresholds'. The verb 'List' and 'Shows' indicate retrieval of information with no modification or side effects.
Attacks that exploit this kind of access
List your current app rules in tru wallet. Shows spending limits, action permissions, and escalation thresholds that control what agents can do on your behalf. Requires login first (use the login tool). It is categorised as a Read tool in the Tru MCP Server, which means it retrieves data without modifying state.
Register the Tru MCP server in PolicyLayer and add a rule for check_rules: 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 Tru. Nothing to install.
check_rules 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 check_rules 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 check_rules. 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.
check_rules is provided by the Tru MCP server (tru-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 →