Run Gau to discover URLs from multiple sources with logging.
AI agents invoke gau_discovery to trigger actions in Bug Bounty MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes Gau, a command-line utility that performs external reconnaissance by querying multiple sources to enumerate URLs. While discovery itself is read-like, the tool's primary function is to run/execute an external scanning operation, which classifies it as Execute.
From the tool's definition Tool description: 'Run Gau to discover URLs from multiple sources with logging.' The verb 'Run' indicates execution of an external tool (Gau, a known OSINT/reconnaissance utility).
Attacks that exploit this kind of access
Run Gau to discover URLs from multiple sources with logging. It is categorised as a Execute tool in the Bug Bounty MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Bug Bounty MCP Server MCP server in PolicyLayer and add a rule for gau_discovery: 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 Bug Bounty MCP Server. Nothing to install.
gau_discovery is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the gau_discovery 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 gau_discovery. 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.
gau_discovery is provided by the Bug Bounty MCP Server MCP server (slanycukr/bugbounty-mcp-server). 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 →