Skip to main content
Glama
SlanyCukr

Bug Bounty MCP Server

by SlanyCukr

gau_discovery

Discovers URLs from multiple sources including Wayback Machine, Common Crawl, OTX, and URLScan for comprehensive web reconnaissance during security assessments.

Instructions

Execute Gau (Get All URLs) for URL discovery from multiple sources with enhanced logging.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
additional_argsNo
blacklistNopng,jpg,gif,jpeg,swf,woff,svg,pdf,css,ico
domainYes
include_subsNo
providersNowayback,commoncrawl,otx,urlscan

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • MCP tool registration and handler for 'gau_discovery'. Proxies parameters to the REST API endpoint '/api/gau' for execution.
    def gau_discovery(
        domain: str,
        providers: str = "wayback,commoncrawl,otx,urlscan",
        include_subs: bool = True,
        blacklist: str = "png,jpg,gif,jpeg,swf,woff,svg,pdf,css,ico",
        additional_args: str = "",
    ) -> dict[str, Any]:
        """Run Gau to discover URLs from multiple sources with logging."""
        data = {
            "domain": domain,
            "providers": providers,
            "include_subs": include_subs,
            "blacklist": blacklist,
            "additional_args": additional_args,
        }
    
        logger.info(f"🔍 Starting Gau URL discovery for {domain}")
        result = api_client.safe_post("api/gau", data)
    
        if result.get("success"):
            logger.info(f"✅ Gau URL discovery completed for {domain}")
        else:
            logger.error("❌ Gau URL discovery failed")
    
        return result
  • Core handler function 'execute_gau' that builds and executes the gau command, parses output, and returns structured results.
    @tool(required_fields=["domain"])
    def execute_gau():
        """Execute Gau (Get All URLs) for URL discovery from multiple sources."""
        data = request.get_json()
        params = extract_gau_params(data)
    
        logger.info(f"Executing Gau on {params['domain']}")
    
        started_at = datetime.now()
        command = build_gau_command(params)
        execution_result = execute_command(command, timeout=params["gau_timeout"])
        ended_at = datetime.now()
    
        return parse_gau_output(execution_result, params, command, started_at, ended_at)
  • Supporting helper functions: extract_gau_params (input validation), build_gau_command (CLI generation), parse_gau_output (result processing).
    def extract_gau_params(data):
        """Extract gau parameters from request data."""
        return {
            "domain": data.get("url", data.get("domain", "")),
            "providers": data.get("providers", "wayback,commoncrawl,otx,urlscan"),
            "include_subs": data.get("include_subs", data.get("include_subdomains", False)),
            "blacklist": data.get("blacklist", ""),
            "from_date": data.get("from_date", ""),
            "to_date": data.get("to_date", ""),
            "output_file": data.get("output_file", ""),
            "threads": data.get("threads", 5),
            "timeout": data.get("timeout", 60),
            "retries": data.get("retries", 5),
            "proxy": data.get("proxy", ""),
            "random_agent": data.get("random_agent", False),
            "verbose": data.get("verbose", False),
            "additional_args": data.get("additional_args", ""),
            "gau_timeout": data.get("gau_timeout", 300),
        }
    
    
    def build_gau_command(params):
        """Build gau command from parameters."""
        command = f"gau {params['domain']}"
    
        if params["providers"] != "wayback,commoncrawl,otx,urlscan":
            command += f" --providers {params['providers']}"
    
        if params["include_subs"]:
            command += " --subs"
    
        if params["blacklist"]:
            command += f" --blacklist {params['blacklist']}"
    
        if params["from_date"]:
            command += f" --from {params['from_date']}"
    
        if params["to_date"]:
            command += f" --to {params['to_date']}"
    
        if params["output_file"]:
            command += f" --output {params['output_file']}"
    
        if params["threads"] != 5:
            command += f" --threads {int(params['threads'])}"
    
        if params["timeout"] != 60:
            command += f" --timeout {int(params['timeout'])}"
    
        if params["retries"] != 5:
            command += f" --retries {int(params['retries'])}"
    
        if params["proxy"]:
            command += f" --proxy {params['proxy']}"
    
        if params["random_agent"]:
            command += " --random-agent"
    
        if params["verbose"]:
            command += " --verbose"
    
        # Handle additional arguments
        if params["additional_args"]:
            command += " " + params["additional_args"]
    
        return command
    
    
    def parse_gau_output(execution_result, params, command, started_at, ended_at):
        """Parse gau execution result and format response."""
        duration_ms = int((ended_at - started_at).total_seconds() * 1000)
    
        if execution_result.get("success"):
            findings = []
            if execution_result.get("stdout"):
                for url in execution_result["stdout"].split("\n"):
                    url = url.strip()
                    if url:
                        finding = {
                            "type": "url",
                            "target": url,
                            "evidence": {
                                "raw_output": url,
                                "tool": "gau",
                                "domain": params["domain"],
                            },
                            "severity": "info",
                            "confidence": "medium",
                            "tags": ["gau"],
                            "raw_ref": url,
                        }
                        findings.append(finding)
    
            payload_bytes = len(execution_result.get("stdout", "").encode("utf-8"))
    
            return {
                "success": True,
                "tool": "gau",
                "params": params,
                "command": command,
                "started_at": started_at.isoformat(),
                "ended_at": ended_at.isoformat(),
                "duration_ms": duration_ms,
                "findings": findings,
                "stats": {
                    "findings": len(findings),
                    "dupes": 0,
                    "payload_bytes": payload_bytes,
                },
            }
        else:
            return {
                "success": False,
                "tool": "gau",
                "params": params,
                "command": command,
                "started_at": started_at.isoformat(),
                "ended_at": ended_at.isoformat(),
                "duration_ms": duration_ms,
                "error": execution_result.get("error", "Command execution failed"),
                "findings": [],
                "stats": {"findings": 0, "dupes": 0, "payload_bytes": 0},
            }
  • Imports gau module to register the Flask endpoint for the gau tool.
    from .gau import gau as gau
  • FastMCP tool decorator registration for 'gau_discovery'.
    @mcp.tool()
    def gau_discovery(
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'enhanced logging' but doesn't specify what that entails (e.g., log levels, output format). It fails to describe critical behaviors like execution time, rate limits, permissions needed, or whether it's a read-only or destructive operation, leaving significant gaps for an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose. It avoids unnecessary words, though it could be slightly more structured by separating purpose from features. Overall, it's appropriately sized with minimal waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 parameters, 0% schema coverage, no annotations) and the presence of an output schema, the description is moderately complete. It states the purpose clearly but lacks parameter details and behavioral context. The output schema may cover return values, but the description doesn't address execution nuances, making it adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for undocumented parameters. It adds no information about the 5 parameters (e.g., 'domain', 'providers', 'blacklist'), their formats, or examples. The mention of 'multiple sources' hints at 'providers' but lacks specifics, failing to provide meaningful semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Execute Gau (Get All URLs) for URL discovery from multiple sources with enhanced logging.' It specifies the verb ('Execute'), resource ('Gau'), and objective ('URL discovery'), though it doesn't explicitly differentiate from sibling tools like 'waybackurls_discovery' or 'subfinder_scan' that might perform similar functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, exclusions, or comparisons to sibling tools such as 'waybackurls_discovery' or 'hakrawler_crawl', which could also be used for URL discovery. Usage is implied by the purpose but not explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SlanyCukr/bugbounty-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server