Get current account information.
AI agents call getAccountInfo to retrieve information from Aster Finance MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While getAccountInfo itself performs a read-only operation (retrieves data without side effects), the classification is elevated from 'low' to 'medium' severity because: (1) the data retrieved includes sensitive financial account details (balances, positions, margin status) on a live cryptocurrency exchange; (2) an AI agent misusing this information in combination with execution tools (like placing orders) could…
From the tool's definition Tool name 'getAccountInfo' and description 'Get current account information' indicate retrieval of account data with no stated modifications.
Attacks that exploit this kind of access
Get current account information. It is categorised as a Read tool in the Aster Finance MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Aster Finance MCP Server MCP server in PolicyLayer and add a rule for getAccountInfo: 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 Aster Finance MCP Server. Nothing to install.
getAccountInfo 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 getAccountInfo 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 getAccountInfo. 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.
getAccountInfo is provided by the Aster Finance MCP Server MCP server (questflowai/aster-mcp-server). 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 →