Count and sample TCP anomalies: retrans, dup ACK, zero window, OOO, RST.
AI agents call pm_tcp_anomalies to retrieve information from PacketMaster without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes existing PCAP capture data to identify and enumerate TCP anomalies. It performs read-only inspection of network traffic patterns without modifying, deleting, or executing any external operations.
From the tool's definition Tool description states it performs 'Count and sample TCP anomalies' with passive analysis operations (retrans, dup ACK, zero window, OOO, RST detection). The term 'count and sample' indicates data retrieval and analysis only.
Attacks that exploit this kind of access
Count and sample TCP anomalies: retrans, dup ACK, zero window, OOO, RST. It is categorised as a Read tool in the PacketMaster MCP Server, which means it retrieves data without modifying state.
Register the PacketMaster MCP server in PolicyLayer and add a rule for pm_tcp_anomalies: 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 PacketMaster. Nothing to install.
pm_tcp_anomalies 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 pm_tcp_anomalies 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 pm_tcp_anomalies. 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.
pm_tcp_anomalies is provided by the PacketMaster MCP server (jctechbr/packetmaster). 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 →