Follow a TCP/UDP/HTTP/TLS stream (truncated, redacted by default).
AI agents call pm_follow_stream 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.
This tool retrieves and analyzes existing PCAP stream data without modifying, deleting, or executing external operations. It is a query/analysis function typical of network diagnostic tools. Severity is medium because malicious use could extract sensitive network communications (credentials, API keys, PII) from captured traffic, though the redaction by default provides some mitigation.
From the tool's definition Tool name 'pm_follow_stream' and description 'Follow a TCP/UDP/HTTP/TLS stream (truncated, redacted by default)' indicate passive analysis of network traffic.
Attacks that exploit this kind of access
Follow a TCP/UDP/HTTP/TLS stream (truncated, redacted by default). 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_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 PacketMaster. Nothing to install.
pm_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 pm_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 pm_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.
pm_follow_stream 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 →