AI agents call theharvester_osint to retrieve information from Redteam without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
theHarvester performs passive OSINT reconnaissance by collecting publicly available information (emails, subdomains, IPs, URLs) from open sources. It does not write, execute code on targets, or destroy data — it is a read/query operation.
From the tool's definition Harvest emails, subdomains, IPs, and URLs from public sources
Attacks that exploit this kind of access
Harvest emails, subdomains, IPs, and URLs from public sources. It is categorised as a Read tool in the Redteam MCP Server, which means it retrieves data without modifying state.
Register the Redteam MCP server in PolicyLayer and add a rule for theharvester_osint: 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 Redteam. Nothing to install.
theharvester_osint 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_osint 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_osint. 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_osint is provided by the Redteam MCP server (samirjani03/redteam-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 →