Skip to main content
Glama
Bug Bounty MCP Server

Bug Bounty MCP Server

by SlanyCukr

Bug Bounty MCP Server

A clean, focused server containing bug bounty hunting workflows and REST API endpoints.

For AI coding assistants, see AGENTS.md for repository-specific guidance.

Features

  • Clean Architecture: Removed bloat and unnecessary dependencies while maintaining core functionality

  • Bug Bounty Focused: Specialized workflows for reconnaissance, vulnerability hunting, business logic testing, OSINT, and file upload testing

  • REST API Endpoints: Simple HTTP API for workflow generation and management

  • Comprehensive Assessments: Combine multiple workflows for complete bug bounty assessments

Related MCP server: BugBounty MCP Server

Architecture

Core Components

  • REST API Server (src/rest_api_server/app.py) - Flask-based HTTP API server with bug bounty workflow endpoints

  • MCP Server (src/mcp_server/app.py) - FastMCP-based server for AI agent communication

  • Bug Bounty Workflows (src/rest_api_server/workflows/) - Specialized workflow generation for different phases of testing

  • Tool Integration (src/rest_api_server/tools/) - Consolidated security tool wrappers

  • Shared Utilities (src/rest_api_server/utils/ & src/rest_api_server/logger.py) - Registry, logging, and helper utilities shared across endpoints

Quick Start

1. Install Dependencies & Start the Server

# Install dependencies with uv
uv sync

# Install development dependencies (optional)
uv sync --dev

# Set up pre-commit hooks (recommended for development)
uv run pre-commit install

# Start the server
uv run -m src.rest_api_server

# Or with environment variables
DEBUG=true BUGBOUNTY_MCP_PORT=8888 uv run -m src.rest_api_server

# Or use the launcher script
./start-server.sh --debug --port 8888

2. Test the API

# Create reconnaissance workflow
curl -X POST http://127.0.0.1:8888/api/bugbounty/reconnaissance-workflow \
  -H "Content-Type: application/json" \
  -d '{"domain": "example.com", "program_type": "web"}'

Configuration

Environment Variables

  • BUGBOUNTY_MCP_PORT: Server port (default: 8888)

  • BUGBOUNTY_MCP_HOST: Server host (default: 127.0.0.1)

  • DEBUG: Enable debug mode (default: false)

Usage Examples

# Start with default configuration
uv run -m src.rest_api_server

# Start with custom configuration
DEBUG=true BUGBOUNTY_MCP_PORT=9999 BUGBOUNTY_MCP_HOST=0.0.0.0 uv run -m src.rest_api_server

Key Features

  1. Bug Bounty Workflow Management: Complete workflow generation for different phases of bug bounty hunting

  2. Vulnerability Prioritization: Intelligence-driven prioritization based on impact and bounty potential

  3. File Upload Testing: Specialized framework for file upload vulnerability testing

  4. OSINT Integration: Comprehensive OSINT gathering workflows

  5. Business Logic Testing: Structured approach to business logic vulnerability discovery

Spec-Kit Integration & AI-Assisted Development

This repository integrates with GitHub Spec-Kit for specification-driven development workflow, enhanced with AI assistance for codebase exploration, planning, and verification.

Gemini CLI Integration

The repository includes integration with Google's Gemini CLI for enhanced AI-powered development assistance:

# Install Gemini CLI (nightly version for latest features)
npx @google/gemini-cli@nightly

Key Use Cases

Codebase Exploration

  • Analyze complex bug bounty tool integrations and workflows

  • Understand relationships between MCP server components and REST API endpoints

  • Navigate through security tool configurations and vulnerability detection patterns

Planning & Specification

  • Generate comprehensive implementation plans for new bug bounty workflows

  • Create detailed specifications for security tool integrations

  • Plan testing strategies for vulnerability detection capabilities

Code Review & Verification

  • Validate implementation quality against security best practices

  • Review bug bounty workflow logic for completeness and accuracy

  • Verify API endpoint security and error handling

  • Analyze tool output parsing and vulnerability classification

Integration with Spec-Kit Workflow

The Gemini CLI complements the existing spec-kit commands:

  1. Specify Phase (.claude/commands/specify.md)

    # Use Gemini CLI to analyze requirements and generate specifications
    npx @google/gemini-cli@nightly analyze-requirements --input "feature_description"
  2. Planning Phase (.claude/commands/plan.md)

    # Use Gemini CLI to validate and enhance implementation plans
    npx @google/gemini-cli@nightly review-plan --spec-file "path/to/spec.md"
  3. Implementation Verification

    # Use Gemini CLI as a code reviewer and security auditor
    npx @google/gemini-cli@nightly audit-security --focus bug-bounty-workflows
# 1. Explore codebase before making changes
npx @google/gemini-cli@nightly explore --focus "bug bounty tools integration"

# 2. Plan new features with AI assistance
npx @google/gemini-cli@nightly plan --spec-driven --security-focused

# 3. Verify implementations against security standards
npx @google/gemini-cli@nightly verify --check-security --validate-workflows

Dependencies

Project uses uv for fast, reliable dependency management:

Core Dependencies

  • Flask: Web framework for REST API

  • FastMCP: MCP server framework

  • Requests: HTTP client library

  • Python 3.11+: Core runtime (supports Python 3.11, 3.12, 3.13)

Development Dependencies

  • Ruff: Fast Python linter and formatter

  • Bandit: Security vulnerability scanner

  • Pydocstyle: Documentation quality checker

  • Pyright: Static type checker

  • Pre-commit: Git pre-commit hooks framework

Install dependencies:

uv sync                # Core dependencies only
uv sync --dev         # Include development tools

Add new dependencies:

uv add package-name

Code Quality

This project enforces code quality through automated pre-commit hooks:

# Install pre-commit hooks
uv run pre-commit install

# Run checks on all files
uv run pre-commit run --all-files

# Run specific checks
uv run ruff check          # Linting
uv run ruff format         # Formatting
uv run bandit -c pyproject.toml # Security scan
uv run pydocstyle          # Documentation check

Standards:

  • Line length: 88 characters

  • Documentation: Google docstring convention

  • Type hints: Required for public APIs

  • Security: Bandit security scanning enabled

Contributing

We welcome contributions. Please see CONTRIBUTING.md for guidelines.

Using an AI coding assistant? Start with AGENTS.md for repository-specific guidance.

Available Tools

40 tools
amass_scanC

Execute Amass for subdomain enumeration with enhanced logging.

Args: domain: Target domain for enumeration mode: Amass mode (enum, intel, viz) additional_args: Additional Amass arguments

Returns: Subdomain enumeration results

Inputs: domain (required), additional_args, mode. Returns: object

analyze_targetC

Analyze target and create comprehensive profile using AI.

Args: target: Target domain, IP, or URL to analyze

Returns: Comprehensive target profile with AI analysis

Inputs: target (required). Returns: object

arjun_parameter_discoveryC

Execute Arjun for HTTP parameter discovery with enhanced logging.

Inputs: url (required), additional_args, delay, method, +3 more. Returns: object

bugbounty_business_logic_workflowC

Create business logic testing workflow for bug bounty hunting.

Args: domain: Target domain program_type: Type of program (web, api, mobile, iot)

Returns: Business logic testing workflow

Inputs: domain (required), program_type. Returns: object

bugbounty_comprehensive_assessmentC

Create comprehensive bug bounty assessment combining all workflows.

Args: domain: Target domain scope: Comma-separated list of in-scope domains/IPs priority_vulns: Comma-separated list of priority vulnerability types include_osint: Include OSINT gathering include_business_logic: Include business logic testing

Returns: Comprehensive bug bounty assessment workflow

Inputs: domain (required), include_business_logic, include_osint, priority_vulns, +1 more. Returns: object

bugbounty_file_upload_testingC

Create file upload vulnerability testing workflow.

Args: target_url: Target URL for file upload testing

Returns: File upload testing workflow with test files

Inputs: target_url (required). Returns: object

bugbounty_osint_workflowC

Create OSINT gathering workflow for bug bounty hunting.

Args: domain: Target domain

Returns: OSINT gathering workflow

Inputs: domain (required). Returns: object

bugbounty_reconnaissance_workflowC

Create comprehensive reconnaissance workflow for bug bounty hunting.

Inputs: domain (required), out_of_scope, program_type, scope. Returns: object

bugbounty_vulnerability_huntingC

Create vulnerability hunting workflow prioritized by impact and bounty potential.

Inputs: domain (required), bounty_range, priority_vulns. Returns: object

create_attack_chainC

Create intelligent attack chain based on target profile.

Args: target: Target domain, IP, or URL objective: Attack objective (comprehensive, fast, stealth, targeted)

Returns: Intelligent attack chain with sequenced tools

Inputs: target (required), objective. Returns: object

dalfox_xss_scanC

Execute Dalfox for advanced XSS vulnerability scanning with enhanced logging.

Inputs: url (required), additional_args, blind, custom_payload, +3 more. Returns: object

dirb_scanC

Execute DIRB directory scanner with enhanced logging.

Args: url: Target URL wordlist: Wordlist file path extensions: File extensions to test recursive: Enable recursive scanning ignore_case: Ignore case sensitivity interactive: Interactive mode additional_args: Additional DIRB arguments

Returns: Directory scanning results

Inputs: url (required), additional_args, extensions, ignore_case, +3 more. Returns: object

dirsearch_scanC

Execute Dirsearch for advanced directory and file discovery with enhanced logging.

Inputs: url (required), additional_args, extensions, recursive, +2 more. Returns: object

dnsenum_scanC

Execute dnsenum for DNS enumeration and subdomain discovery.

Args: domain: Target domain dns_server: DNS server to use wordlist: Wordlist for brute force threads: Number of threads delay: Delay between requests reverse: Enable reverse DNS lookup additional_args: Additional dnsenum arguments

Returns: DNS enumeration results

Inputs: domain (required), additional_args, delay, dns_server, +3 more. Returns: object

feroxbuster_scanA

Execute Feroxbuster for fast recursive directory scanning.

Args: url: Target URL wordlist: Wordlist file path threads: Number of concurrent threads depth: Maximum recursion depth extensions: File extensions to search for filter_codes: HTTP status codes to filter out timeout: Request timeout in seconds additional_args: Additional Feroxbuster arguments

Returns: Recursive directory discovery results

Inputs: url (required), additional_args, depth, extensions, +4 more. Returns: object

ffuf_scanC

Execute FFuf for web fuzzing with enhanced logging.

Inputs: url (required), additional_args, match_codes, mode, +1 more. Returns: object

fierce_scanC

Execute Fierce for DNS reconnaissance and subdomain discovery.

Args: domain: Target domain dns_server: DNS server to use wordlist: Custom wordlist for subdomain brute force threads: Number of threads delay: Delay between requests wide: Wide scan (more comprehensive) additional_args: Additional Fierce arguments

Returns: DNS reconnaissance results

Inputs: domain (required), additional_args, delay, dns_server, +3 more. Returns: object

gau_discoveryC

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

Inputs: domain (required), additional_args, blacklist, include_subs, +1 more. Returns: object

gobuster_scanB

Execute Gobuster to find directories, DNS subdomains, or virtual hosts with enhanced logging.

Args: url: Target URL or domain mode: Scan mode (dir, dns, vhost, fuzz) wordlist: Wordlist file path extensions: File extensions to search for threads: Number of threads timeout: Request timeout user_agent: Custom User-Agent cookies: Cookies to include additional_args: Additional Gobuster arguments

Returns: Directory and subdomain discovery results

Inputs: url (required), additional_args, cookies, extensions, +5 more. Returns: object

hakrawler_crawlB

Execute hakrawler for fast web crawling and endpoint discovery.

Args: url: Target URL to crawl depth: Crawling depth forms: Extract form endpoints robots: Parse robots.txt sitemap: Parse sitemap wayback: Include Wayback Machine URLs insecure: Skip TLS verification additional_args: Additional hakrawler arguments

Returns: Web crawling and endpoint discovery results

Inputs: url (required), additional_args, depth, forms, +4 more. Returns: object

httpx_probeC

Execute HTTPx for HTTP probing with enhanced logging.

Args: targets: Target URLs or IPs target_file: File containing targets ports: Ports to probe methods: HTTP methods to use status_code: Filter by status code content_length: Show content length output_file: Output file path additional_args: Additional HTTPx arguments

Returns: HTTP probing results

Inputs: additional_args, content_length, methods, output_file, +4 more. Returns: object

jaeles_vulnerability_scanC

Execute Jaeles for advanced vulnerability scanning with custom signatures.

Inputs: url (required), additional_args, config, signatures, +2 more. Returns: object

katana_crawlD

Execute Katana for next-generation crawling and spidering with enhanced logging.

Inputs: url (required), additional_args, depth, form_extraction, +2 more. Returns: object

masscan_high_speedC

Execute Masscan for high-speed port scanning.

Args: target: Target IP address or CIDR range ports: Port range to scan rate: Packet transmission rate banners: Enable banner grabbing exclude_file: File containing IPs to exclude include_file: File containing IPs to include output_format: Output format (list, xml, json) additional_args: Additional Masscan arguments

Returns: High-speed scan results

Inputs: target (required), additional_args, banners, exclude_file, +4 more. Returns: object

nikto_scanB

Execute Nikto web server vulnerability scanner.

Args: target: Target hostname or IP address port: Port number to scan ssl: Use SSL/HTTPS plugins: Nikto plugins to run output_format: Output format (txt, xml, csv) evasion: Evasion techniques to use additional_args: Additional Nikto arguments

Returns: Web server vulnerability scan results

Inputs: target (required), additional_args, evasion, output_format, +3 more. Returns: object

nmap_advanced_scanB

Execute advanced Nmap scan with comprehensive options for bug bounty hunting.

Args: target: Target IP or hostname scan_type: Scan technique (-sS, -sT, -sU, etc.) ports: Port specification timing: Timing template (-T0 to -T5) scripts: NSE scripts to run os_detection: Enable OS detection service_detection: Enable service version detection aggressive: Enable aggressive scan mode stealth: Enable stealth scan options additional_args: Additional arguments

Returns: Advanced scan results

Inputs: target (required), additional_args, aggressive, os_detection, +6 more. Returns: object

nmap_scanC

Execute an enhanced Nmap scan against a target with real-time logging.

Args: target: The IP address or hostname to scan scan_type: Scan type (e.g., -sV for version detection, -sC for scripts) ports: Comma-separated list of ports or port ranges additional_args: Additional Nmap arguments

Returns: Scan results with enhanced telemetry

Inputs: target (required), additional_args, ports, scan_type. Returns: object

nuclei_scanC

Execute Nuclei vulnerability scanner with enhanced logging and comprehensive parameter support.

Inputs: target (required), additional_args, author, automatic_scan, +31 more. Returns: object

optimize_parametersC

Optimize tool parameters using AI based on target profile.

Args: target: Target domain, IP, or URL tool: Tool name to optimize parameters for context: Additional context or constraints

Returns: Optimized parameters and configuration

Inputs: target (required), tool (required), context. Returns: object

paramspider_miningC

Execute ParamSpider for parameter mining from web archives with enhanced logging.

Inputs: domain (required), additional_args, exclude, level, +1 more. Returns: object

rustscan_fast_scanC

Execute RustScan for ultra-fast port scanning.

Args: target: Target IP address or hostname ports: Custom port range (default: all ports) ulimit: File descriptor limit batch_size: Batch size for port scanning timeout: Socket timeout in milliseconds tries: Number of tries per port no_nmap: Skip nmap integration additional_args: Additional RustScan arguments

Returns: Fast port scan results

Inputs: target (required), additional_args, batch_size, no_nmap, +4 more. Returns: object

select_toolsB

AI-powered tool selection based on target profile.

Args: target: Target domain, IP, or URL objective: Scan objective (comprehensive, fast, stealth, targeted)

Returns: Optimized tool selection with recommendations

Inputs: target (required), objective. Returns: object

smart_scanC

Execute intelligent scan using AI-driven tool selection with parallel execution.

Args: target: Target domain, IP, or URL objective: Scan objective (comprehensive, fast, stealth, targeted)

Returns: Smart scan results with AI-optimized execution

Inputs: target (required), objective. Returns: object

sqlmap_scanC

Execute SQLMap for SQL injection testing with enhanced logging.

Inputs: url (required), additional_args, data. Returns: object

subfinder_scanC

Execute Subfinder for passive subdomain enumeration with enhanced logging.

Args: domain: Target domain silent: Run in silent mode all_sources: Use all sources additional_args: Additional Subfinder arguments

Returns: Passive subdomain enumeration results

Inputs: domain (required), additional_args, all_sources, silent. Returns: object

wafw00f_scanB

Execute wafw00f to identify Web Application Firewall (WAF) protection.

Args: target: Target URL findall: Find all possible WAFs proxy: Proxy server to use headers: Custom HTTP headers output_file: Output file path additional_args: Additional wafw00f arguments

Returns: WAF detection results

Inputs: target (required), additional_args, findall, headers, +2 more. Returns: object

waybackurls_discoveryC

Execute Waybackurls for historical URL discovery with enhanced logging.

Inputs: domain (required), additional_args, get_versions, no_subs. Returns: object

wfuzz_scanB

Execute Wfuzz for web application fuzzing.

Args: url: Target URL with FUZZ keyword wordlist: Wordlist file path fuzz_parameter: Parameter to fuzz (default: FUZZ) hide_codes: HTTP status codes to hide threads: Number of concurrent threads follow_redirects: Follow HTTP redirects additional_args: Additional Wfuzz arguments

Returns: Web application fuzzing results

Inputs: url (required), additional_args, follow_redirects, fuzz_parameter, +3 more. Returns: object

wpscan_analyzeC

Execute WPScan for WordPress vulnerability analysis.

Args: url: WordPress site URL enumerate: Enumeration options (ap=all plugins, at=all themes, etc.) update: Update WPScan database random_user_agent: Use random User-Agent api_token: WPVulnDB API token threads: Number of threads additional_args: Additional WPScan arguments

Returns: WordPress vulnerability analysis results

Inputs: url (required), additional_args, api_token, enumerate, +3 more. Returns: object

x8_parameter_discoveryC

Execute x8 for hidden parameter discovery with enhanced logging.

Inputs: url (required), additional_args, body, headers, +2 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.7/5.0

    Scored across 40 tools

    Disambiguation3/5

    The tools cover distinct security tools and workflows (e.g., amass_scan for subdomain enumeration, nuclei_scan for vulnerability scanning), but there is significant overlap in purpose. For example, dirb_scan, dirsearch_scan, feroxbuster_scan, and gobuster_scan all perform directory/file discovery, which could confuse an agent. Similarly, nmap_scan and nmap_advanced_scan are redundant, and multiple tools handle subdomain enumeration (amass_scan, dnsenum_scan, fierce_scan, subfinder_scan). Descriptions help differentiate, but the overlaps are substantial.

    Naming Consistency4/5

    Most tools follow a consistent verb_noun pattern (e.g., amass_scan, dnsenum_scan, nuclei_scan), which is clear and predictable. However, there are minor deviations: some tools use underscores inconsistently (e.g., bugbounty_business_logic_workflow lacks underscores in 'bugbounty'), and a few tools have longer, more descriptive names (e.g., bugbounty_comprehensive_assessment). Overall, the naming is mostly consistent and readable, with only slight variations.

    Tool Count2/5

    With 40 tools, the count is excessive for a bug bounty server, leading to bloat and potential confusion. Many tools are redundant (e.g., multiple directory scanners, multiple subdomain enumerators) or could be consolidated into broader workflows. A well-scoped server for this domain should typically have 10-20 tools to cover core functionalities without overwhelming the agent. The high number suggests poor scoping and unnecessary fragmentation.

    Completeness5/5

    The tool set is highly complete for bug bounty hunting, covering all major aspects: reconnaissance (e.g., subdomain enumeration, crawling), vulnerability scanning (e.g., XSS, SQL injection, WAF detection), workflow creation (e.g., business logic testing, OSINT), and AI-enhanced features (e.g., analyze_target, optimize_parameters). There are no obvious gaps; agents have tools for every stage from target analysis to comprehensive assessment, ensuring no dead ends in typical workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      AI-powered cybersecurity automation platform with 150+ security tools and 12+ autonomous AI agents for penetration testing, vulnerability assessment, and bug bounty hunting. Enables comprehensive security testing through intelligent tool selection and automated workflows.
      3
      -
    • A
      license
      B
      quality
      D
      maintenance
      Enables comprehensive security testing and penetration testing through natural language conversations with 92+ tools for reconnaissance, vulnerability assessment, web application testing, OSINT, and reporting. Designed for authorized bug bounty hunting and security assessments.
      53
      44
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      AI-powered bug bounty hunting platform that integrates security tools (OWASP ZAP, Caido, Burp Suite) for automated reconnaissance, vulnerability testing, JavaScript analysis, and finding management with PostgreSQL storage.
      47
      51
      MIT