AI agents call billing_history to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical billing data for audit or informational purposes. While the data may be sensitive (financial records), the tool itself performs no write, execute, destructive, or financial transaction operations—it only queries existing records. The blast radius of misuse is limited to information disclosure rather than actual financial movement or system compromise.
From the tool's definition Tool name 'billing_history' combined with description 'View billing ledger history for the agent' clearly indicates a retrieval operation. The verb 'View' and the passive sense (historical data access) confirm read-only semantics with no modification.
Attacks that exploit this kind of access
View billing ledger history for the agent. It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for billing_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 Run402. Nothing to install.
billing_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 billing_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 billing_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.
billing_history is provided by the Run402 MCP server (kychee-com/run402). 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 →