get_premium_index
AI agents call get_premium_index to retrieve information from Aster Info without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves market data without modifying, deleting, or executing code. It fits the 'Read' category as a data retrieval operation. Severity is low because accessing market data poses minimal risk even if misused by an AI agent. Confidence is moderate (0.8) due to the absence of a description, but the strong contextual evidence from sibling tools and server purpose mitigates this uncertainty.
From the tool's definition Tool name 'get_premium_index' and server context indicate data retrieval from Aster DEX market data. Sibling tools (get_kline, get_order_book, get_latest_price, get_funding_rate_history, etc.) are all read-only market data queries.
Attacks that exploit this kind of access
get_premium_index. It is categorised as a Read tool in the Aster Info MCP Server, which means it retrieves data without modifying state.
Register the Aster Info MCP server in PolicyLayer and add a rule for get_premium_index: 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 Info. Nothing to install.
get_premium_index 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_premium_index 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_premium_index. 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_premium_index is provided by the Aster Info MCP server (kukapay/aster-info-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 →