Search Shodan
AI agents call shodan_search to retrieve information from Mcp Shodan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Shodan search retrieves publicly indexed information about internet-connected devices and vulnerabilities without modifying data. However, severity is medium rather than low because the search results can expose sensitive infrastructure information that could be used to identify attack targets or plan reconnaissance, creating moderate risk if an AI agent searches for vulnerable systems inappropriately.
From the tool's definition Tool name 'shodan_search' with description 'Search Shodan' indicates querying/retrieval from the Shodan database. The server description confirms it provides 'tools for IP lookups, device searches, DNS lookups, vulnerability queries' — all read operations.
Attacks that exploit this kind of access
Search Shodan. It is categorised as a Read tool in the Mcp Shodan MCP Server, which means it retrieves data without modifying state.
Register the Mcp Shodan MCP server in PolicyLayer and add a rule for shodan_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 Mcp Shodan. Nothing to install.
shodan_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 shodan_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 shodan_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.
shodan_search is provided by the Mcp Shodan MCP server (w0h1v/mcp-shodan). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.