AI agents call perps_get_positions to retrieve information from Logiqical without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'Get' and the absence of any language indicating state modification, deletion, or execution confirm this is a read-only query. It retrieves financial position data from Hyperliquid but does not move money, execute trades, or modify accounts. While the data concerns financial positions, the tool itself performs no financial transaction.
From the tool's definition Tool name 'perps_get_positions' and description 'Get current perps positions and margin summary' indicate a data retrieval operation with no modification of state.
Attacks that exploit this kind of access
Get current perps positions and margin summary from Hyperliquid. It is categorised as a Read tool in the Logiqical MCP Server, which means it retrieves data without modifying state.
Register the Logiqical MCP server in PolicyLayer and add a rule for perps_get_positions: 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 Logiqical. Nothing to install.
perps_get_positions 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 perps_get_positions 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 perps_get_positions. 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.
perps_get_positions is provided by the Logiqical MCP server (logiqical-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 →