start_mining · Refinore MCP: Risk & Policy

WHAT IT DOES

What start_mining does on Refinore

AI agents invoke start_mining to trigger actions in Refinore. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why start_mining needs a policy

This tool initiates mining sessions that execute transactions on a blockchain. While mining itself is not irreversible (the sibling tool 'delete_strategy' and 'edit_session' suggest sessions can be modified or terminated), the act of deploying funds and starting a mining operation constitutes execution of code/transactions with real financial consequences.

From the tool's definition Tool description states it 'Start[s] a new ORE mining session' and 'Deploys SOL/USDC/ORE across squares on the mining grid.' This involves executing a blockchain transaction that initiates mining operations with configurable parameters (amount, number of…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_mining Rate-limited

start_mining stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_mining": {
      "limits": [
        {
          "counter": "start_mining_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Refinore, so you can run agents against it safely.

FAQ

Questions about start_mining

What does the start_mining tool do? +

Start a new ORE mining session on refinORE. Deploys SOL/USDC/ORE across squares on the mining grid. Configure amount, number of squares, token, risk tolerance, and tile selection strategy. It is categorised as a Execute tool in the Refinore MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_mining? +

Register the Refinore MCP server in PolicyLayer and add a rule for start_mining: 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.

What risk level is start_mining? +

start_mining is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_mining? +

Yes. Add a rate_limit block to the start_mining 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.

How do I block start_mining completely? +

Set action: deny in the PolicyLayer policy for start_mining. 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.

What MCP server provides start_mining? +

start_mining 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.