Deep dive on traffic between two IP addresses (optional port).
AI agents call pm_troubleshoot_flow 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.
The tool queries and analyzes network traffic patterns within an existing PCAP file without modifying, deleting, or executing external operations. This is a classic Read operation with minimal blast radius since it only retrieves insights from captured network data.
From the tool's definition Tool performs 'Deep dive on traffic between two IP addresses' — a data retrieval and analysis operation on PCAP files. No modification, deletion, or command execution is described.
Attacks that exploit this kind of access
Deep dive on traffic between two IP addresses (optional port). 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_troubleshoot_flow: 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_troubleshoot_flow 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_troubleshoot_flow 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_troubleshoot_flow. 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_troubleshoot_flow 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 →