Subtract duration from a date/time
AI agents call subtract_time to retrieve information from MCP Time Server Node without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a pure date/time arithmetic calculation — subtracting a duration from a datetime value. It computes and returns a result without modifying any external state, storing data, or triggering side effects. It is a read/compute operation, consistent with sibling tools like add_time, calculate_duration, and convert_timezone which are all stateless time manipulation utilities.
From the tool's definition Subtract duration from a date/time
Attacks that exploit this kind of access
Subtract duration from a date/time. It is categorised as a Read tool in the MCP Time Server Node MCP Server, which means it retrieves data without modifying state.
Register the MCP Time Server Node MCP server in PolicyLayer and add a rule for subtract_time: 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 MCP Time Server Node. Nothing to install.
subtract_time 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 subtract_time 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 subtract_time. 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.
subtract_time is provided by the MCP Time Server Node MCP server (pshempel/mcp-time-server-node). 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 →