AI agents call usenami_perp_funding_spread to retrieve information from Usenami without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval operation querying funding rate spreads across exchanges. No write, execute, destructive, or financial transaction capabilities are present. The tool simply fetches and presents existing market information. Low severity because misuse would only affect data visibility, not cause operational harm or financial impact.
From the tool's definition Tool returns data snapshot ('Returns the cross-venue funding-rate spread snapshot') with no indication of modification, deletion, or side effects. It retrieves market data across venues.
Attacks that exploit this kind of access
Returns the cross-venue funding-rate spread snapshot for a base ticker. It is categorised as a Read tool in the Usenami MCP Server, which means it retrieves data without modifying state.
Register the Usenami MCP server in PolicyLayer and add a rule for usenami_perp_funding_spread: 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 Usenami. Nothing to install.
usenami_perp_funding_spread 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 usenami_perp_funding_spread 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 usenami_perp_funding_spread. 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.
usenami_perp_funding_spread is provided by the Usenami MCP server (namixai/usenami-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 →