Get L2 order book depth for a specific asset from Hyperliquid.
AI agents call get_l2_orderbook to retrieve information from Hyperliquid 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 (order book depth) without creating orders, executing trades, modifying positions, or moving funds. It has no side effects and is purely informational. While it is part of a trading platform, the tool itself only reads data, making it a Read category risk with minimal blast radius.
From the tool's definition Tool name and description indicate it 'Get[s] L2 order book depth for a specific asset'—a data retrieval operation with no modification, execution, or financial commitment. Querying market data is a read-only operation.
Attacks that exploit this kind of access
Get L2 order book depth for a specific asset from Hyperliquid. It is categorised as a Read tool in the Hyperliquid MCP Server, which means it retrieves data without modifying state.
Register the Hyperliquid MCP server in PolicyLayer and add a rule for get_l2_orderbook: 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 Hyperliquid. Nothing to install.
get_l2_orderbook 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_l2_orderbook 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_l2_orderbook. 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_l2_orderbook is provided by the Hyperliquid MCP server (midodimori/hyperliquid-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 →