AI agents call follow_stream to retrieve information from Tshark without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on established Wireshark/TShark functionality, 'follow_stream' retrieves and displays packet stream reassembly data. It has no side effects—it only queries and presents captured network data. The sibling tools include analysis and capture operations, but this tool specifically follows the read-only pattern of data inspection.
From the tool's definition Tool name 'follow_stream' in packet analysis context (TShark/Wireshark ecosystem). No description provided, but in packet capture/analysis tools, 'follow stream' is a standard read-only feature that reconstructs and displays TCP/UDP/SSL stream data from pcap…
Attacks that exploit this kind of access
follow_stream. It is categorised as a Read tool in the Tshark MCP Server, which means it retrieves data without modifying state.
Register the Tshark MCP server in PolicyLayer and add a rule for 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 Tshark. Nothing to install.
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 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 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.
follow_stream is provided by the Tshark MCP server (ouonet/tshark-mcp). 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 →