AI agents call check_scope 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.
This tool only previews/checks scope eligibility and explicitly states it does not make any actual queries or modifications. It is a gating mechanism for other tools, returning authorization status rather than data or triggering operations. This is fundamentally a read operation with minimal risk—it merely informs whether subsequent actions are permitted.
From the tool's definition Tool name 'check_scope' and description 'Preview the scope gate result' indicate a read-only operation that checks whether a target is within HackerOne scope without performing any action or retrieval of sensitive data.
Attacks that exploit this kind of access
Preview the scope gate result for a target WITHOUT making any. 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 check_scope: 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.
check_scope 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 check_scope 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 check_scope. 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.
check_scope 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 →