Get the in-scope assets for a bug bounty program. Auto-paginates to return all scope items. Returns asset types, identifiers, bounty eligibility, and severity caps.
AI agents call get_program_scope to retrieve information from HackerOne MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries program scope information without side effects. It returns data about which assets are in scope for a bug bounty program, which is informational only. No data is created, modified, deleted, or executed. The 'auto-paginates to return all scope items' further confirms this is a read operation that processes results for display.
From the tool's definition Tool description states 'Get the in-scope assets' and 'Returns asset types, identifiers, bounty eligibility, and severity caps' — purely retrieval operations with no modification, deletion, or execution.
Documented attack patterns abuse exactly the kind of access get_program_scope gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HackerOne MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_program_scope:
{
"version": "1",
"default": "deny",
"tools": {
"get_program_scope": {}
}
}get_program_scope is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the in-scope assets for a bug bounty program. Auto-paginates to return all scope items. Returns asset types, identifiers, bounty eligibility, and severity caps. It is categorised as a Read tool in the HackerOne MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HackerOne MCP Server MCP server in PolicyLayer and add a rule for get_program_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 HackerOne MCP Server. Nothing to install.
get_program_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 get_program_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 get_program_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.
get_program_scope is provided by the HackerOne MCP Server MCP server (sicks3c/hackerone-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 HackerOne MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 HackerOne MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.