AI agents call validate_strategy_script 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.
The tool performs validation and probing of external data sources to check a strategy script before it is saved. It returns validation errors but does not execute, create, modify, or delete any strategies or blockchain state. The validation is a prerequisite check (Read category) rather than an Execute operation, which would occur when the strategy is actually applied.
From the tool's definition Tool description states it 'Validate[s]' and 'Probes external JSON sources and returns path-based validation errors' — these are read-only validation operations with no data modification, deletion, or execution of the strategy itself.
Attacks that exploit this kind of access
Validate a deterministic custom strategy script before saving it. Probes external JSON sources and returns path-based validation errors. 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 validate_strategy_script: 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.
validate_strategy_script 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 validate_strategy_script 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 validate_strategy_script. 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.
validate_strategy_script 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 →