AI agents call check_spending 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 financial data (spending history and budget status) without making any changes to accounts, subscriptions, or financial commitments. It is a read-only query operation that returns user information. While the data is financial in nature, the tool itself does not move money, create charges, or commit financial obligations — it only displays existing data.
From the tool's definition Tool name is 'check_spending' and description states it 'Check[s] how much you've spent' and 'Shows remaining budget' — purely informational queries with no modification, creation, deletion, or execution of operations.
Attacks that exploit this kind of access
Check how much you've spent today, this week, and this month across all apps. Shows remaining budget based on your spending rules. 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_spending: 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_spending 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_spending 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_spending. 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_spending 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 →