AI agents invoke pcap_start to trigger actions in Packmate. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of a predefined pcap file processing operation. Although it reads/analyzes traffic data (not destructive), the act of 'begin processing' constitutes an Execute action that starts an external operation. It is not a simple Read (which would be passive retrieval) because it initiates a process.
From the tool's definition 'Begin processing the configured pcap file' indicates execution of a process or analysis operation on a pcap file, which triggers external processing whose effects depend on file configuration and system state.
Attacks that exploit this kind of access
Begin processing the configured pcap file (FILE mode only). It is categorised as a Execute tool in the Packmate MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Packmate MCP server in PolicyLayer and add a rule for pcap_start: 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 Packmate. Nothing to install.
pcap_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the pcap_start 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 pcap_start. 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.
pcap_start is provided by the Packmate MCP server (umbra2728/packmate-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 →