AI agents call get_klines to retrieve information from Asterdex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical market data (candlesticks) which is a passive query operation. It has no side effects on account state, positions, or financial transactions. Historical kline data is static reference information used for analysis. Confidence is high because the name and description unambiguously describe a data retrieval operation with no destructive or transactional capability.
From the tool's definition Tool name 'get_klines' and description 'Get historical candlestick (kline) data' indicate a data retrieval operation. Klines (candlestick data) are historical, read-only market information with no ability to modify accounts, execute trades, or move funds.
Attacks that exploit this kind of access
Get historical candlestick (kline) data. It is categorised as a Read tool in the Asterdex MCP Server, which means it retrieves data without modifying state.
Register the Asterdex MCP server in PolicyLayer and add a rule for get_klines: 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 Asterdex. Nothing to install.
get_klines 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_klines 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_klines. 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_klines is provided by the Asterdex MCP server (tyranosurasmax/asterdex-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 →