AI agents call zeek_query_http 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 operation that retrieves historical network security monitoring data from HTTP logs. While it doesn't modify data, the severity is medium rather than low because HTTP logs can contain sensitive information (credentials in URLs, user agents revealing system details, IP addresses), and an AI agent with unrestricted access could exfiltrate or analyze this data inappropriately.
From the tool's definition Tool searches and queries Zeek HTTP request logs with filtering on host, URI, user agent, and status code. Terms like 'search,' 'query,' and 'filtering' indicate read-only data retrieval operations with no modification or deletion of logs.
Attacks that exploit this kind of access
Search Zeek HTTP request logs. Supports wildcard matching on host and URI, user agent filtering, and status code filtering. 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_query_http: 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_query_http 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_query_http 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_query_http. 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_query_http 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 →