AI agents call get_account_info 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 is a straightforward information retrieval tool. It returns static account metadata (wallet address, deposit instructions) without modifying state, executing code, or affecting financial transactions. The worst-case misuse is an AI agent discovering its own wallet details, which poses minimal risk. Classified as Read with low severity due to lack of blast radius from accidental misuse.
From the tool's definition Tool retrieves account information (wallet address and deposit instructions) via 'Get your refinORE account info'.
Attacks that exploit this kind of access
Get your refinORE account info including Solana wallet address and deposit instructions. Call this first to discover your wallet. 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_account_info: 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_account_info 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_account_info 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_account_info. 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_account_info 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 →