theharvester_shodan · theHarvester MCP Server MCP

WHAT IT DOES

What theharvester_shodan does on theHarvester MCP Server

AI agents invoke theharvester_shodan to trigger actions in theHarvester MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why theharvester_shodan needs a policy

This tool executes an external OSINT command (theHarvester) over SSH on a Kali Linux system, integrating with Shodan to perform active network reconnaissance. It triggers external operations (Shodan API queries, potential active probing) whose results depend on the target arguments.

From the tool's definition 'Run theHarvester with Shodan integration to get detailed host information including open ports and banners' — actively executes a reconnaissance tool via SSH on a Kali Linux host, querying Shodan for live host data including open ports and service banners

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

theharvester_shodan Rate-limited

theharvester_shodan stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "theharvester_shodan": {
      "limits": [
        {
          "counter": "theharvester_shodan_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches theHarvester MCP Server, so you can run agents against it safely.

FAQ

Questions about theharvester_shodan

What does the theharvester_shodan tool do? +

Run theHarvester with Shodan integration to get detailed host information including open ports and banners. It is categorised as a Execute tool in the theHarvester MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on theharvester_shodan? +

Register the theHarvester MCP Server MCP server in PolicyLayer and add a rule for theharvester_shodan: 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.

What risk level is theharvester_shodan? +

theharvester_shodan is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit theharvester_shodan? +

Yes. Add a rate_limit block to the theharvester_shodan 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.

How do I block theharvester_shodan completely? +

Set action: deny in the PolicyLayer policy for theharvester_shodan. 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.

What MCP server provides theharvester_shodan? +

theharvester_shodan 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.