AI agents call get_all_mids to retrieve information from Hyperliquid Info without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and peer tools all perform data queries without side effects. 'mids' likely refers to mid-prices (midpoint between bid/ask spreads), a common read operation in trading APIs. No indication of data modification, execution, deletion, or financial transactions. Classified as Read with high confidence despite missing description.
From the tool's definition Tool name 'get_all_mids' follows the 'get_' prefix pattern consistent with sibling tools (get_candles_snapshot, get_l2_snapshot, get_perp_metadata, etc.) which are all read-only data retrieval operations.
Documented attack patterns abuse exactly the kind of access get_all_mids gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hyperliquid Info, and nothing reaches the server without passing your rules. This is the rule we recommend for get_all_mids:
{
"version": "1",
"default": "deny",
"tools": {
"get_all_mids": {}
}
}get_all_mids is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_all_mids. It is categorised as a Read tool in the Hyperliquid Info MCP Server, which means it retrieves data without modifying state.
Register the Hyperliquid Info MCP server in PolicyLayer and add a rule for get_all_mids: 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 Info. Nothing to install.
get_all_mids 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_all_mids 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_all_mids. 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_all_mids is provided by the Hyperliquid Info MCP server (kukapay/hyperliquid-info-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hyperliquid Info, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Hyperliquid Info tools catalogued and risk-classified — across an index of 43,000+ MCP servers.