detect_ivt
AI agents call detect_ivt to retrieve information from Supply Ops Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
IVT detection is a diagnostic analysis function that examines patterns and flags suspicious activity; it does not modify data, execute commands, delete records, or move money. It retrieves or analyzes existing data to produce insights. The lack of a description makes it difficult to be certain, but the name and server purpose (diagnostic/compliance checking) suggest pure analysis.
From the tool's definition Tool name 'detect_ivt' and server context indicate detection/analysis of Invalid Traffic (IVT), a read-only diagnostic operation. No description provided, which lowers confidence slightly.
Attacks that exploit this kind of access
detect_ivt. It is categorised as a Read tool in the Supply Ops Agent MCP Server, which means it retrieves data without modifying state.
Register the Supply Ops Agent MCP server in PolicyLayer and add a rule for detect_ivt: 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 Supply Ops Agent. Nothing to install.
detect_ivt 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 detect_ivt 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 detect_ivt. 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.
detect_ivt is provided by the Supply Ops Agent MCP server (mpessis/supply-ops-agent). 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 →