Follow a TCP or UDP stream in a locally synced PCAP and extract the full payload exchange. Reconstructs the application-layer conversation showing the complete back-and-forth (e.g., HTTP request/response, FTP login, DNS exchange). Returns both ASCII and hex representations. Use wireshark_conversa...
AI agents call wireshark_follow_stream 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 retrieves network packet data from PCAP files with no modification or deletion capability—purely a query/analysis operation. However, severity is high (not low/medium) because the 'blast radius' of misuse is significant: an AI agent could use this to extract sensitive application-layer data including login credentials, API tokens, session identifiers, and confidential communications from captured…
From the tool's definition Tool description states it will 'extract the full payload exchange' and 'reconstruct the application-layer conversation showing the complete back-and-forth' from network traffic. It returns 'both ASCII and hex representations' of intercepted data.
Attacks that exploit this kind of access
Follow a TCP or UDP stream in a locally synced PCAP and extract the full payload exchange. Reconstructs the application-layer conversation showing the complete back-and-forth (e.g., HTTP request/response, FTP login, DNS exchange). Returns both ASCII and hex representations. Use wireshark_conversations first to identify interesting stream IDs. Sync the PCAP first using wireshark_sync_pcap. Required: pcap_name. Optional: stream_id (default: 0), stream_type (. 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_follow_stream: 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_follow_stream 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_follow_stream 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_follow_stream. 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_follow_stream 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 →