BugBounty

v1.0.0Securitystable

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 hunti

bugbounty-mcp-servermcpai-integration
Share:
32
Stars
0
Downloads
0
Weekly
0/5

What is BugBounty?

BugBounty is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables comprehensive security testing and penetration testing through natural language conversations with 92+ tools for reconnaissance, vulnerability assessment, web application testing, osint, and r...

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 hunti

This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables comprehensive security testing and penetration testi

Use Cases

Conduct comprehensive security testing with 92+ reconnaissance and vulnerability assessment tools.
Execute authorized penetration testing through natural language conversations.
Generate security reports and findings from web application testing campaigns.
gokulapap

Maintainer

LicenseMIT License
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx bugbounty-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use BugBounty

BugBounty MCP Server is a Python-based security testing platform that exposes 92+ offensive security tools through the Model Context Protocol, enabling natural language-driven penetration testing conversations with Claude or other AI clients. It covers the full bug bounty lifecycle — subdomain enumeration, port scanning, vulnerability assessment (SQLi, XSS, SSRF, IDOR, and more), OSINT, exploitation, and report generation — all with a configurable safe-mode system to restrict testing to authorized targets only.

Prerequisites

  • Docker and Docker Compose for the recommended containerized installation (or Python 3.x and pip for native install)
  • API keys for optional enrichment services: SHODAN_API_KEY, VIRUSTOTAL_API_KEY, CENSYS_API_ID, CENSYS_API_SECRET, GITHUB_TOKEN, SECURITYTRAILS_API_KEY, HUNTER_IO_API_KEY, BINARYEDGE_API_KEY
  • Written authorization for all targets before running any tests
  • An MCP client such as Claude Desktop
1

Clone the repository

Clone the BugBounty MCP Server repository to your local machine.

git clone https://github.com/gokulapap/bugbounty-mcp-server.git && cd bugbounty-mcp-server
2

Configure environment variables

Copy the example environment file and add your API keys for the enrichment services you plan to use. Tools that rely on a missing API key will be unavailable but others will still function.

cp env.example .env
3

Configure allowed targets (safe mode)

Edit the safety block in your config to restrict testing to authorized domains and IP ranges. The safe_mode and allowed_targets settings are enforced at the tool level before any network requests are made.

# In your config file:
# safety:
#   safe_mode: true
#   allowed_targets: ["*.example.com", "192.168.1.0/24"]
#   blocked_targets: ["*.gov", "*.mil"]
#   rate_limit_enabled: true
#   requests_per_second: 10.0
4

Start the server with Docker Compose

Build and launch the containerized server. Check logs to confirm all 92+ tools loaded successfully.

docker-compose up --build -d && docker-compose logs -f bugbounty-mcp
5

Add to Claude Desktop configuration

For native (non-Docker) installations, configure Claude Desktop to launch the server via the run.sh script. For Docker, use the HTTP transport pointing at the container.

{
  "mcpServers": {
    "bugbounty-mcp": {
      "command": "/path/to/bugbounty-mcp-server/run.sh",
      "args": ["serve"]
    }
  }
}
6

Validate the configuration

Use the built-in validation command to confirm the server loaded all tools and the environment is configured correctly before running live tests.

./run.sh validate-config && ./run.sh list-tools

BugBounty Examples

Client configuration

Native installation config for Claude Desktop. For Docker deployments, replace with an HTTP transport URL pointing at the container's exposed port.

{
  "mcpServers": {
    "bugbounty-mcp": {
      "command": "/path/to/bugbounty-mcp-server/run.sh",
      "args": ["serve"],
      "env": {
        "SHODAN_API_KEY": "your_shodan_key",
        "VIRUSTOTAL_API_KEY": "your_vt_key",
        "GITHUB_TOKEN": "your_github_token"
      }
    }
  }
}

Prompts to try

All prompts below should only be run against targets for which you have explicit written authorization.

- "Enumerate subdomains for example.com using both passive and active techniques"
- "Test the login form at https://example.com/login for SQL injection vulnerabilities"
- "Perform a comprehensive security assessment of example.com including ports, SSL, and common web vulnerabilities"
- "Research Example Corp for employee contact information and recent data breaches using OSINT tools"
- "Generate an executive security report summarizing all findings from this session"

Troubleshooting BugBounty

Tools relying on third-party APIs return authentication or rate-limit errors

Check that the corresponding API key environment variable is set correctly in your .env file (e.g. SHODAN_API_KEY, VIRUSTOTAL_API_KEY). Run './run.sh validate-config' to surface missing or malformed keys. Each service has its own free-tier rate limits — consult the provider's dashboard if you are hitting limits.

Target blocked by safe mode even though it is an authorized target

Edit the allowed_targets list in your config to include the exact domain or CIDR range. Wildcard patterns like '*.example.com' do not automatically match the apex domain 'example.com' — add both entries explicitly if needed.

Docker Compose build fails or container exits immediately

Run 'docker-compose logs bugbounty-mcp' to inspect startup errors. Common causes are missing system tools (nmap, gobuster, etc.) that failed to install during the image build. Ensure Docker has sufficient disk space and that your Docker daemon is up to date.

Frequently Asked Questions about BugBounty

What is BugBounty?

BugBounty is a Model Context Protocol (MCP) server that 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 hunti It connects AI assistants to external tools and data sources through a standardized interface.

How do I install BugBounty?

Follow the installation instructions on the BugBounty GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with BugBounty?

BugBounty works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is BugBounty free to use?

Yes, BugBounty is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

BugBounty Alternatives — Similar Security Servers

Looking for alternatives to BugBounty? Here are other popular security servers you can use with Claude, Cursor, and VS Code.

Casdoor

13.6k

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

ghidraMCP

9.0k

An Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through

HexStrike AI

8.9k

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b

IDA Pro MCP

8.7k

Enables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.

Anthropic Cybersecurity Skills

6.6k

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform

Hooker

5.1k

🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u

Browse More Security MCP Servers

Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "bugbounty-mcp-server": { "command": "npx", "args": ["-y", "bugbounty-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use BugBounty?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides