Automated first-pass triage of a PCAP file. Produces a single structured report combining: capture overview (packets, bytes, duration, rates), protocol breakdown, top talkers (sources, destinations, conversations, ports), TCP health summary (retransmissions, dup ACKs, zero windows, out-of-order, ...
AI agents call wireshark_pcap_triage to retrieve information from Wireshark MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes a PCAP file to produce a structured report. It performs no writes, executions, or destructive operations — purely passive inspection and reporting of captured network traffic. Severity is medium because it can expose sensitive network metadata including credentials-adjacent data (TLS SNI, DNS queries, top talkers), but the tool itself only reads/analyzes existing capture files.
From the tool's definition Automated first-pass triage of a PCAP file. Produces a single structured report combining: capture overview, protocol breakdown, top talkers, TCP health summary, DNS summary, TLS summary, anomaly indicators
Attacks that exploit this kind of access
Automated first-pass triage of a PCAP file. Produces a single structured report combining: capture overview (packets, bytes, duration, rates), protocol breakdown, top talkers (sources, destinations, conversations, ports), TCP health summary (retransmissions, dup ACKs, zero windows, out-of-order, RSTs with health score), DNS summary (queries, NXDOMAIN rate, top domains), TLS summary (SNI, versions), anomaly indicators, and recommended next tools to run. This should be the FIRST tool called on any new PCAP. Sync the PCAP first using wireshark_sync_pcap. Required: pcap_name. It is categorised as a Read tool in the Wireshark MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Wireshark MCP Server MCP server in PolicyLayer and add a rule for wireshark_pcap_triage: 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 Wireshark MCP Server. Nothing to install.
wireshark_pcap_triage 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 wireshark_pcap_triage 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 wireshark_pcap_triage. 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.
wireshark_pcap_triage is provided by the Wireshark MCP Server MCP server (presidio-federal/wireshark-mcp-container). 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 →