AI agents call current_datetime to retrieve information from Web without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure information retrieval tool that queries system state (current datetime) without modifying anything. It belongs in the Read category as it simply retrieves and formats existing data. Severity is low because misuse poses minimal risk—an AI could at worst use incorrect time for decision-making, but cannot damage systems or data.
From the tool's definition Tool returns current date and time information with no side effects. Description states it returns data in a read-only format; there is no indication of any data modification, deletion, or execution capability.
Attacks that exploit this kind of access
Return the current date and time in an unambiguous human-readable format, including timezone and locale information. It is categorised as a Read tool in the Web MCP Server, which means it retrieves data without modifying state.
Register the Web MCP server in PolicyLayer and add a rule for current_datetime: 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 Web. Nothing to install.
current_datetime 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 current_datetime 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 current_datetime. 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.
current_datetime is provided by the Web MCP server (ryandam/essentialmcp). 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 →