AI agents call shodan_search 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 search retrieves publicly available internet scan data without modifying or deleting anything. This is a Read operation (query/search). Severity is medium rather than low because Shodan queries can expose sensitive infrastructure details that could aid attackers in reconnaissance, though the server implements scope gating against HackerOne programs to mitigate misuse.
From the tool's definition Tool name 'shodan_search' on a 'Passive reconnaissance MCP server' that performs searches; sister tool descriptions reference 'host lookups, search, and DNS queries'; no description provided for this specific tool but context indicates it queries data.
Attacks that exploit this kind of access
shodan_search. 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_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 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 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 →