Fetch candlestick data from Binance public API
AI agents call binance_klines to retrieve information from MCP Binance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical and real-time candlestick (OHLCV) price data from a public API. It performs no writes, deletions, executions, or financial transactions — only data retrieval. The public API nature further limits risk. Severity is low because misuse would only affect the agent's decision-making based on incorrect data interpretation, with no external consequences or data loss.
From the tool's definition Tool description states 'Fetch candlestick data from Binance public API' — a pure retrieval operation with no side effects.
Attacks that exploit this kind of access
Fetch candlestick data from Binance public API. It is categorised as a Read tool in the MCP Binance MCP Server, which means it retrieves data without modifying state.
Register the MCP Binance MCP server in PolicyLayer and add a rule for binance_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 MCP Binance. Nothing to install.
binance_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 binance_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 binance_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.
binance_klines is provided by the MCP Binance MCP server (shukehi/crypto-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 →