AI agents call zeek_connection_summary to retrieve information from Zeek without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is purely a read/query operation over Zeek connection logs. It performs aggregation and statistical analysis on existing data without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal — an attacker could only gain insights into network traffic patterns already captured in logs, not manipulate them or trigger external actions.
From the tool's definition Tool retrieves a 'statistical summary of connections' and metrics like 'top talkers, services, bytes, and connection counts' — querying and aggregating existing log data with no side effects.
Attacks that exploit this kind of access
Get statistical summary of connections over a time period - top talkers, services, bytes, and connection counts. It is categorised as a Read tool in the Zeek MCP Server, which means it retrieves data without modifying state.
Register the Zeek MCP server in PolicyLayer and add a rule for zeek_connection_summary: 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 Zeek. Nothing to install.
zeek_connection_summary 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 zeek_connection_summary 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 zeek_connection_summary. 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.
zeek_connection_summary is provided by the Zeek MCP server (solomonneas/zeek-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 →