AI agents invoke start_strategy 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.
This tool executes a complex blockchain operation (mining session launch) whose real-world effects depend on the strategy content and market conditions. While mining itself generates tokens rather than destroying them, the execution of an automated financial operation on-chain that consumes resources (gas, computational time) and produces tokens warrants Execute classification.
From the tool's definition start_strategy 'Launches an auto-mining session' — this triggers an autonomous operation on the Solana blockchain that executes a mining strategy with real financial consequences (token generation, gas fees, rewards allocation).
Attacks that exploit this kind of access
Start mining using a saved strategy. Launches an auto-mining session with the 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.
Register the Refinore MCP server in PolicyLayer and add a rule for start_strategy: 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.
start_strategy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_strategy 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 start_strategy. 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.
start_strategy 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 →