AI agents call get_current_round to retrieve information from Refinore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves public mining round information without modifying any state, creating side effects, or affecting other users. It is a simple data query operation with no blast radius—misuse by an AI agent cannot cause harm to assets, accounts, or the platform. Classified as Read with low severity.
From the tool's definition Tool name and description indicate retrieval of read-only public data: 'Get the current mining round info' with fields like 'round number, time remaining, total deployed, motherlode, and expected value'.
Attacks that exploit this kind of access
Get the current mining round info — round number, time remaining, total deployed, motherlode, and expected value. This is a public endpoint (no auth required). It is categorised as a Read tool in the Refinore MCP Server, which means it retrieves data without modifying state.
Register the Refinore MCP server in PolicyLayer and add a rule for get_current_round: 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 Refinore. Nothing to install.
get_current_round 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 get_current_round 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 get_current_round. 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.
get_current_round is provided by the Refinore MCP server (jusscubs/refinore-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 →