Protocol distribution tree from tshark -z io,phs.
AI agents call pm_protocol_hierarchy 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.
pm_protocol_hierarchy retrieves and queries protocol statistics from PCAP files without creating, modifying, or deleting data. It is a passive analysis tool that reports metrics on captured traffic, fitting the Read category. Severity is low because the tool only reports statistics and has no side effects on the network or system state.
From the tool's definition Tool uses tshark's read-only io,phs statistic option to generate a protocol distribution tree from PCAP files.
Attacks that exploit this kind of access
Protocol distribution tree from tshark -z io,phs. 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_protocol_hierarchy: 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_protocol_hierarchy 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_protocol_hierarchy 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_protocol_hierarchy. 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_protocol_hierarchy 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 →