AI agents call get_packet_statistics 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.
This tool performs passive data retrieval and analysis of existing network packet captures. It generates summary statistics from PCAP files without side effects, making changes to files, executing external operations, or handling financial transactions. The primary use case is read-only inspection of network traffic metadata.
From the tool's definition Tool name is 'get_packet_statistics' and description states it 'Get statistics about packets in a PCAP file' — a query operation that retrieves and analyzes aggregated data without modifying, executing code, or deleting anything.
Attacks that exploit this kind of access
Get statistics about packets in a PCAP file. 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 get_packet_statistics: 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.
get_packet_statistics 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 get_packet_statistics 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 get_packet_statistics. 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.
get_packet_statistics 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 →