AI agents call accrued_interest to retrieve information from Shikamaru without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The accrued_interest tool computes a financial metric (simple interest accrual) from input parameters without creating, modifying, deleting, or executing external operations. It is a pure calculation function analogous to a query or fetch operation.
From the tool's definition Tool performs a deterministic calculation of accrued interest between two dates using provided inputs (notional, rate, day-count fraction).
Attacks that exploit this kind of access
Exact simple accrued interest (notional * rate * day-count fraction) between two dates. Dates are ISO YYYY-MM-DD; rate is the annual rate as a decimal (0.05 = 5%). Deterministic. It is categorised as a Read tool in the Shikamaru MCP Server, which means it retrieves data without modifying state.
Register the Shikamaru MCP server in PolicyLayer and add a rule for accrued_interest: 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 Shikamaru. Nothing to install.
accrued_interest 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 accrued_interest 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 accrued_interest. 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.
accrued_interest is provided by the Shikamaru MCP server (JayOfemi/shikamaru). 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 →