Compare current network activity against a baseline and identify statistical outliers. Flags hosts with unusual byte volumes, connection counts, port diversity, or timing patterns that deviate significantly from the norm.
AI agents call zeek_detect_outliers 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.
zeek_detect_outliers performs statistical analysis and querying over network security monitoring data to detect anomalies. It reads logs, computes baselines, and reports findings—characteristic Read operations with no side effects. The tool does not execute code, trigger external actions, create/modify records, or delete data.
From the tool's definition Tool description states it 'Compare[s] current network activity against a baseline and identify[s] statistical outliers' and 'Flags hosts' — purely analytical operations that retrieve and analyze existing log data without modifying, executing external…
Attacks that exploit this kind of access
Compare current network activity against a baseline and identify statistical outliers. Flags hosts with unusual byte volumes, connection counts, port diversity, or timing patterns that deviate significantly from the norm. 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_detect_outliers: 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_detect_outliers 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_detect_outliers 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_detect_outliers. 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_detect_outliers 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 →