AI agents call current_time to retrieve information from Meridian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval operation that queries timezone information and returns the current local time. It has no side effects, cannot modify state, and poses no risk of destructive, financial, or unintended execution. The blast radius of misuse is minimal—worst case an agent retrieves incorrect time data for decision-making, but cannot cause irreversible harm.
From the tool's definition Tool retrieves current time data across specified IANA timezones with no modification, creation, deletion, or execution of external operations. Description explicitly states 'Get the current time' indicating a query/lookup operation.
Attacks that exploit this kind of access
Get the current time across one or more IANA timezones. It is categorised as a Read tool in the Meridian MCP Server, which means it retrieves data without modifying state.
Register the Meridian MCP server in PolicyLayer and add a rule for current_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 Meridian. Nothing to install.
current_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 current_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 current_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.
current_time is provided by the Meridian MCP server (marcusicaro/meridian-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 →