AI agents call usenami_perp_oracle_families 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 read operation that queries metadata about which oracle families are used by different perpetual futures trading venues. It has no side effects—no transactions are created, no data is modified, and no external operations are triggered. The blast radius of misuse is minimal; an AI agent cannot cause financial loss or harm by calling this tool.
From the tool's definition Tool returns oracle family classification data for perpetual futures venues. The verb 'returns' indicates data retrieval with no modification.
Attacks that exploit this kind of access
Returns the oracle family classification for 30+ perp venues — useful. 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_oracle_families: 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_oracle_families 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_oracle_families 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_oracle_families. 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_oracle_families 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 →