MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Comprehensive MCP (Managed Command Platform) Server for Bug Bounty Command Line Tools with standardized JSON output
-
A modular external attack surface mapping tool integrating tools for automated reconnaissance and bug bounty workflows.
★ 78 -
Production-grade OWASP ZAP MCP server for authorized penetration testing and bug-bounty workflows (67 curated tools, authenticated scanning, target authorization policy).
MIT -
One command installs 670+ security tools on Debian/Ubuntu/Kali, Fedora, Arch, openSUSE and Termux. Its authorization-gated MCP server runs them in a disposable Kata Containers VM sandbox for Claude Code, Codex, Gemini CLI, OpenCode and other MCP clients. 872 agent skills for CTF, pentesting, bug bounty, DFIR and red/blue teams.
oci MIT ★ 98 -
defi-security-mcpupdated this year
MCP server for RektWatch — exposes DeFi protocol risk scores, incidents, audits, and bug bounties as Claude tools with automatic x402 USDC payment handling
npm MIT -
All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI agent, it enables tasks like pentesting, bug bounty hunting, threat hunting, and more.
MIT ★ 219 -
Hexstrike-redteamgithub.com/Yenn503/Hexstrike-redteamupdated this year
AI-powered MCP penetration testing framework combining HexStrike's 150+ security tools with BOAZ's advanced payload evasion (77+ loaders, 12 encoders). Features 12+ autonomous AI agents for bug bounty, CTF, CVE intelligence, exploit generation, and red team operations.
pypi ★ 174 -
mcp-security-atlasgithub.com/Avinash333-D/mcp-security-atlasupdated this year
An advanced MCP server integrating industry-standard security tools (Nmap, ZAP, Metasploit, Burp) for automated vulnerability research and reconnaissance. Designed for ethical hackers and bug bounty hunters to streamline the 'recon-to-report' workflow via a unified LLM interface.
Apache-2.0 -
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 bridge LLMs with real-world offensive security capabilities.
★ 1 -
hexstrike-aigithub.com/0x4m4/hexstrike-aiupdated this year
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 bridge LLMs with real-world offensive security capabilities.
MIT ★ 13,615 -
AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy, stealth browser, autonomous AI agent. Built on Tauri + Rust + React.
MIT ★ 52 -
revqlgithub.com/e4ac/revqlactive
GraphQL object reverse lookup tool
GPL-3.0 ★ 3 -
MCP server that connects AI assistants to HackerOne for bug bounty hunting
MIT ★ 360 -
AI Pentesting Framework, Bug Bounty MCP Server, SAST/DAST Taint Engine & 12 Offensive Security Skills for Claude Code, Google Antigravity, Codex & Cursor.
MIT ★ 7 -
Daily sweep of live, payable open-source bounties (Algora, Opire, GitHub) with repo-liveness checks and spam filtering. Publishes HTML/RSS/JSON, an MCP server for AI agents, and a Cloudflare Worker API.
MIT -
mergen-mcpgithub.com/g4sk0/mergen-mcpupdated this year
Mergen is an MCP server that gives your AI a real red team brain. It doesn't just run tools, it picks the right ones, chains them together, and actually makes sense of the output. Built by pentesters, for pentesters who are tired of babysitting scripts.
MIT ★ 17 -
Connect your AI assistant to HackerOne by syncing bounty data and enabling detailed search and analysis with MCP-compatible tools.
MIT ★ 1 -
Autonomous Offensive Security Agent for Red Team Operations
Apache-2.0 ★ 4 -
Free, self-hosted bug bounty scope tracker: new programs, new targets, fee and reward changes, repo pushes across HackerOne, Bugcrowd, Intigriti, YesWeHack, HackenProof and Sherlock. CLI, HTTP API, MCP server. No API keys.
MIT ★ 3 -
Evidence-first prototype pollution scanner with safe client, server, SCA, and MCP workflows
MIT -
MCP Server for Meta Hackers, use agents to create FBDL scripts. FBDL is a tool designed to help you quickly and efficiently setup security bug reproduction steps using a standard “bug” description language.
MIT ★ 9 -
hackerone-mcpgithub.com/lordx64/hackerone-mcpupdated this year
Zero-dependency MCP server exposing HackerOne's public GraphQL API as AI-agent tools: discover bounty programs, scopes, and recently solved reports.
MIT -
security-mcp-servergithub.com/security/security-ai-mcpupdated this year
Security AI MCP Server - Advanced security testing and automation framework with 70+ tools
pypi MIT -
pentest-autopilot-mcpsgithub.com/bankai-max-wow/pentest-autopilot-mcpsupdated this year
Professional MCP servers for penetration testing automation - SQLi, Exploit, Auth, Recon
NOASSERTION ★ 1 -
Burp-MCP-Security-Analysis-Toolkitgithub.com/SnailSploit/Burp-MCP-Security-Analysis-Toolkitupdated this year
Burp MCP Security Analysis Toolkit
MIT ★ 21 -
Scope-locked agent harness that drives Burp Suite over MCP for authorised security testing
MIT ★ 2 -
okalstergithub.com/0PeterAdel/okalsterupdated this year
Okalster — an open platform for autonomous security hunting agents powered by MCP, skills, and intelligent tool orchestration.
Apache-2.0 ★ 1 -
MCP server for headless browser automation with Playwright - Non-commercial license
NOASSERTION ★ 1 -
Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself.
go MIT ★ 1,836 -
burp-mcpgithub.com/Den-Sec/burp-mcpupdated this year
Burp Suite Professional MCP server - 61 tools to drive Burp from an AI agent (Claude Code) for authorized security testing.
MIT ★ 3 -
Security pentesting MCP Server with 89 tools across 10 categories. Windows/WSL bridge for Kali tools integration with Claude.
MIT ★ 4 -
Agentic web-scanning engine with a terminal workspace, specialist tools, browser validation, reports, REST and MCP.
Apache-2.0 ★ 183 -
Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural language conversation.
MIT ★ 21 -
Scope-locked reconnaissance, passive security auditing, scan diffing, and stdio MCP server CLI written in Rust with compile-time and socket-level IP guards.
Apache-2.0 -
the-box-mcpgithub.com/horizonfps/the-box-mcpupdated this year
MCP daemon that gives an agentic coding client a native offensive-security toolchain: MITM proxy, app graph, OOB server, CVE/report RAG and 103 tools.
MIT ★ 2 -
🛡️ Autonomous Offensive AI Framework & Cognitive Multi-Agent Swarm for Red Teams & Penetration Testers. Polyglot Engine (C++20 SIMD, Rust Tokio, Go Prober, Python Swarm) with Zero False-Positive Proof Capsules & MCP Server.
MIT ★ 3 -
MCP server that gives AI agents authorized-only offensive-security tools: recon, CVE intel, JS analysis, port scanning
pypi MIT -
Open-source, self-hosted web pentesting suite with agentic scanning, analyst tools, API testing, model checkpoints and MCP integrations.
Apache-2.0 ★ 386 -
86-tool OSINT MCP server with private evidence graphs, image analysis, reverse search, and person dossiers.
MIT ★ 71 -
flameshot-mcpgithub.com/Willian-2-0-0-1/flameshot-mcpupdated this year
Servidor MCP do Flameshot: seu agente tira o print e marca a evidencia sozinho - retangulo, seta, texto, blur e numeradores por chamada de ferramenta
MIT ★ 1 -
JavaScript attack-surface recon for authorized security testing: endpoints, secrets, dangerous sinks, CORS/JWT issues, CVEs, and GraphQL — with JSON/HTML/SARIF reports. Use as a CLI, a GitHub Action, or an MCP server.
MIT ★ 3 -
secai - agentic cybersecurity engine: 272 capability scripts (93 detection skills + 176 tools, 121 ported from 995 concepts), Rust core + one contract, MCP, offline-first triage. No proof, no report.
NOASSERTION ★ 1 -
Authorized Android pentest lab, drivable by hand or by AI — Frida bypass chain, live traffic capture with automatic IDOR flagging, full MCP control plane, web dashboard.
MIT ★ 9 -
burpsuite-for-ai-agentgithub.com/whoismemas/burpsuite-for-ai-agentupdated this year
Two-way Burp Suite MCP bridge for AI agents — capture traffic, queue scan tasks, send findings back to Burp as Scanner issues or Repeater tabs. MCP server + Jython plugin.
MIT -
h1mcpgithub.com/uunw/h1mcpactive
HackerOne MCP server in Rust — full HackerOne API coverage (reports, programs, scope, payouts, hacktivity) + local draft management, exposed as Model Context Protocol tools for Claude Desktop, Claude Code, and any MCP client.
MIT -
A power tool for web security testing — scanner, repeater, intruder, and AI agent in one Rust binary. No accounts, no telemetry, no cloud.
NOASSERTION ★ 1 -
AI-powered MCP server for Burp Suite Professional — 149 tools across proxy, scanner, inline fuzzer, race conditions, guided injection, JWT/IDOR attacks, recon & OOB, with a real-time dashboard and hardened localhost security. Drive Burp from Claude Code or any MCP client.
MIT ★ 308 -
MCP server exposing offensive recon tooling to LLM agents — Claude Code, OpenCode, Codex, Hermes. 10 tools: subdomain enum, DNS, http probe, tech detect, WAF detect, origin bypass, wayback, port scan, endpoint discover, nuclei. uvx one-liner, zero API keys.
MIT ★ 2 -
bearstrike-aigithub.com/Roshu18/bearstrike-aiupdated this year
🐻 BearStrike AI: High-Signal Pentesting Console (MCP-First, Model-Agnostic). Build fast, low-noise security workflows with queue-first execution, skills-aware planning, and 150+ integrated tools.
MIT ★ 8 -
Scope-gated, modular security MCP server — 205 tools across 26 skill packs (red/blue/OSINT/cloud/AD/post-ex/IoT/Wi-Fi/AI-LLM/mobile/forensics/CTF) with an attack-path engine, credential vault & ATT&CK reporting. For authorized engagements.
MIT -
debugvault-mcpgithub.com/tarigha/debugvault-mcpupdated this year
Official MCP server for DebugVault — search 5,530+ production bugs, get AI-powered debugging, and post bounties directly from Cursor, Claude, and Cline
npm MIT -
osint-mcp-servergithub.com/badchars/osint-mcp-serverupdated this year
OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.
npm MIT ★ 62 -
Self-hosted attack-surface recon — point it at a domain you own and map subdomains, DNS, TLS, HTTP, CDN, and historical URLs in one dashboard. The same tools run over MCP, so AI agents (Claude Code, Cline) can drive recon too.
MIT ★ 2 -
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your own agent.
MIT ★ 3,417 -
keelgithub.com/lutfizp/keelactive
Keel is the MCP control plane for authorized pentests and bug bounty. Plug it into Claude Code, Codex, Cursor, OpenCode, Hermes, Copilot, and any other MCP client. Keel runs scoped recon, keeps the target from getting hammered, and turns scanner noise into hunter-grade findings.
pypi MIT ★ 2