OHLCV candles for a market.
AI agents call get_candles to retrieve information from Lighter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical candlestick data for a perpetual market. It performs no write, execution, deletion, or financial operations—it only reads and returns market information. The blast radius of misuse is minimal since providing incorrect historical data does not cause direct harm or irreversible changes.
From the tool's definition Tool name 'get_candles' and description 'OHLCV candles for a market' indicate data retrieval. OHLCV (Open, High, Low, Close, Volume) candles are historical market data with no side effects.
Attacks that exploit this kind of access
OHLCV candles for a market. It is categorised as a Read tool in the Lighter MCP MCP Server, which means it retrieves data without modifying state.
Register the Lighter MCP server in PolicyLayer and add a rule for get_candles: 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 Lighter MCP. Nothing to install.
get_candles 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_candles 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_candles. 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_candles is provided by the Lighter MCP server (0xdegenmo/lighter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_candles is one line of Lighter's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →