AI agents call zeek_long_connections 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 a read-only analytical tool that searches historical network connection logs for anomalies. It has no capability to modify data, execute commands, delete records, or trigger external actions. The worst-case misuse would be information disclosure about network patterns, which carries low blast radius. Classification as Read is appropriate.
From the tool's definition Tool queries and analyzes existing Zeek logs to 'find unusually long-lived connections' — it performs pattern detection and retrieval over network security monitoring data without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Find unusually long-lived connections that may indicate C2 beacons, tunnels, or persistent backdoors. 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_long_connections: 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_long_connections 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_long_connections 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_long_connections. 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_long_connections 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 →