Run theHarvester to gather OSINT on a domain. Collects emails, subdomains, hosts, IPs, and URLs from various public sources.
AI agents call theharvester_search to retrieve information from theHarvester MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs reconnaissance by querying public OSINT sources to retrieve domain-related information. While theHarvester is a reconnaissance tool that could support malicious reconnaissance activities, the tool itself is read-only—it queries and aggregates publicly available information without modifying data, executing code on target systems, or triggering destructive operations.
From the tool's definition Tool description states it 'gather[s] OSINT on a domain' and 'Collects emails, subdomains, hosts, IPs, and URLs from various public sources.' The verb 'gather' and 'collects' indicate passive data retrieval with no modification or execution of external…
Attacks that exploit this kind of access
Run theHarvester to gather OSINT on a domain. Collects emails, subdomains, hosts, IPs, and URLs from various public sources. It is categorised as a Read tool in the theHarvester MCP Server MCP Server, which means it retrieves data without modifying state.
Register the theHarvester MCP Server MCP server in PolicyLayer and add a rule for theharvester_search: 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 theHarvester MCP Server. Nothing to install.
theharvester_search 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_search 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_search. 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_search is provided by the theHarvester MCP Server MCP server (schwarztim/sec-theharvester-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 →