AI agents call date_diff to retrieve information from Basic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
date_diff is a pure computational utility that retrieves or derives information from input parameters without creating, modifying, deleting, or executing operations. It falls squarely under Read category. Severity is low because misuse would only produce incorrect date calculations with no blast radius beyond the calculation result itself.
From the tool's definition Tool performs date arithmetic calculation—'Calculate the difference between two dates'—with no side effects, data modification, or external state changes.
Attacks that exploit this kind of access
Calculate the difference between two dates. Use this for date arithmetic. It is categorised as a Read tool in the Basic MCP Server, which means it retrieves data without modifying state.
Register the Basic MCP server in PolicyLayer and add a rule for date_diff: 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 Basic. Nothing to install.
date_diff 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 date_diff 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 date_diff. 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.
date_diff is provided by the Basic MCP server (msilverblatt/basic-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 →