AI agents call shodan_host to retrieve information from Shodan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Shodan host lookup retrieves publicly indexed information about IP addresses/hosts (open ports, services, vulnerabilities, banners, geolocation). This is a Read operation—passive reconnaissance with no data modification. However, severity is 'high' because detailed host information can inform attack planning; misuse could enable targeting of systems.
From the tool's definition Tool name 'shodan_host' on a Shodan reconnaissance server indicates host lookup capability. Sibling tools like 'shodan_search' and 'shodan_dns' confirm data retrieval operations. Server description states 'host lookups' explicitly.
Attacks that exploit this kind of access
shodan_host. It is categorised as a Read tool in the Shodan MCP Server, which means it retrieves data without modifying state.
Register the Shodan MCP server in PolicyLayer and add a rule for shodan_host: 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 Shodan. Nothing to install.
shodan_host 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 shodan_host 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 shodan_host. 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.
shodan_host is provided by the Shodan MCP server (tobiasguta/shodan-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 →