AI agents call follow_tls_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.
The tool appears to retrieve and display TLS stream data from captured packets, which is a read operation. However, the absence of a description and the involvement of TLS decryption capabilities on this server elevates confidence uncertainty and severity slightly above 'low' due to potential sensitivity of accessing decrypted TLS streams (which could expose credentials or private data if misused by an agent).
From the tool's definition Tool name 'follow_tls_stream' suggests following/reading TLS stream data from network packets. No description provided, but context indicates this is part of TShark packet analysis functionality.
Attacks that exploit this kind of access
follow_tls_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_tls_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_tls_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_tls_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_tls_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_tls_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 →