AI agents call server_time to retrieve information from Kraken Pro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information without modifying any state, executing code, or affecting financial positions. Despite the server's overall purpose (trading and financial operations), this specific tool is a simple read-only query. Severity is low because misuse of this tool by an AI agent cannot cause harm—it cannot move money, delete data, or trigger unintended orders.
From the tool's definition Tool name is 'server_time' and description states it retrieves 'Kraken server time (UTC)'. This is a pure query operation with no side effects—it only fetches current time data from the server.
Documented attack patterns abuse exactly the kind of access server_time gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kraken Pro MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for server_time:
{
"version": "1",
"default": "deny",
"tools": {
"server_time": {}
}
}server_time is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Kraken server time (UTC). It is categorised as a Read tool in the Kraken Pro MCP MCP Server, which means it retrieves data without modifying state.
Register the Kraken Pro MCP server in PolicyLayer and add a rule for server_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 Kraken Pro MCP. Nothing to install.
server_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 server_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 server_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.
server_time is provided by the Kraken Pro MCP server (oilst/kraken-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kraken Pro MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Kraken Pro MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.