get_klines
AI agents call get_klines to retrieve information from Binance Cryptocurrency MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical candlestick/kline data for cryptocurrency pairs. It is a read-only query operation that retrieves publicly available market data without creating, modifying, executing code, deleting data, or moving funds. The blast radius of misuse is minimal—an agent could potentially retrieve large volumes of data or make excessive requests, but cannot cause financial harm or system damage.
From the tool's definition Tool name 'get_klines' and server description indicating access to 'candlestick charts' and 'market data'. Klines are candlestick data points (open, high, low, close, volume) used in technical analysis.
Attacks that exploit this kind of access
get_klines. It is categorised as a Read tool in the Binance Cryptocurrency MCP MCP Server, which means it retrieves data without modifying state.
Register the Binance Cryptocurrency 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 Binance Cryptocurrency MCP. 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 Binance Cryptocurrency MCP server (jianchundev/binance-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 →