Email addresses, subdomains, and hosts harvester from public sources.
AI agents call theHarvester to retrieve information from MCP Kali Pentest without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
theHarvester performs reconnaissance by aggregating publicly available information. It has no destructive, write, execute, or financial capabilities - it purely reads and enumerates data from public sources. While useful in a pentest workflow, the tool itself performs no side effects, code execution, or irreversible actions.
From the tool's definition Tool explicitly 'harvester[s]' data 'from public sources' - retrieves/queries publicly available information without modifying or deleting anything.
Attacks that exploit this kind of access
Email addresses, subdomains, and hosts harvester from public sources. It is categorised as a Read tool in the MCP Kali Pentest MCP Server, which means it retrieves data without modifying state.
Register the MCP Kali Pentest MCP server in PolicyLayer and add a rule for theHarvester: 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 MCP Kali Pentest. Nothing to install.
theHarvester 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 theHarvester 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 theHarvester. 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.
theHarvester is provided by the MCP Kali Pentest MCP server (root1856/mcpkali). 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 →