subscribe_market_data
AI agents call subscribe_market_data to retrieve information from Hyperliquid MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name implies subscribing to market data, which is a read/query operation retrieving live market information. However, the empty description lowers confidence. Given the sibling tools context (market analysis tools like get_candles, get_funding_rates, get_l2_orderbook), this likely retrieves streaming market data without side effects. Confidence is reduced due to the empty description.
From the tool's definition Tool name 'subscribe_market_data' suggests subscribing to/reading market data feeds; description is empty and uninformative.
Attacks that exploit this kind of access
subscribe_market_data. It is categorised as a Read tool in the Hyperliquid MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hyperliquid MCP Server MCP server in PolicyLayer and add a rule for subscribe_market_data: 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 MCP Server. Nothing to install.
subscribe_market_data 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 subscribe_market_data 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 subscribe_market_data. 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.
subscribe_market_data is provided by the Hyperliquid MCP Server MCP server (jhonatanpinheiro/hyperliquid-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 →