AI agents call check_history 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | integer | — | Number of recent charges to show (default: 10) |
status | string | — | Filter by status: pending, approved, completed, rejected, cancelled |
Parameters from the server's own tool schema.
This tool retrieves historical transaction data from a wallet without creating, modifying, deleting, or executing any operations. It is purely informational, fitting the Read category. Severity is low because viewing transaction history poses minimal risk even if misused by an AI agent—it only exposes data the authenticated user already has access to.
From the tool's definition Tool description explicitly states 'View recent charges and payment activity' and 'Shows the most recent transactions with status, amount, and source.' These are read-only retrieval operations with no modification or side effects.
Attacks that exploit this kind of access
View recent charges and payment activity in your tru wallet. Shows the most recent transactions with status, amount, and source. 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.
check_history accepts 2 parameters: limit, status. The full parameter table on this page comes from the server's own tool schema.
Register the Tru MCP server in PolicyLayer and add a rule for check_history: 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_history 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_history 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_history. 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_history 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 →