現在日時を返す基本機能
AI agents call when-is-now to retrieve information from Local Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves temporal information from the server without modifying, executing external operations, or affecting system state. It is a pure read operation providing contextual data (current time). No destructive, financial, or execution capabilities are present. Low severity due to minimal security impact if misused—an agent cannot cause harm by repeatedly querying the current time.
From the tool's definition Tool description states it returns 'current date and time' (現在日時を返す). The server description explicitly indicates it 'retrieve[s] the current date and time in ISO 8601 format'. This is a query operation with no side effects.
Attacks that exploit this kind of access
現在日時を返す基本機能. It is categorised as a Read tool in the Local Context MCP Server, which means it retrieves data without modifying state.
Register the Local Context MCP server in PolicyLayer and add a rule for when-is-now: 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 Local Context. Nothing to install.
when-is-now 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 when-is-now 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 when-is-now. 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.
when-is-now is provided by the Local Context MCP server (obaratch/local-context-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 →