AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Security & Safety/
hexstrike-ai
hexstrike-ai logo

hexstrike-ai

Active·★ 13.1k·MIT·Updated 2026-08-03

HexStrike AI MCP Agents is a penetration-testing and cybersecurity automation framework that connects AI agents such as Claude, GPT or Copilot to a large toolbox through the Model Context Protocol. Version 6.0 is described as a multi-agent architecture with an intelligent decision engine for tool selection, parameter optimisation and attack-chain discovery, 12+ autonomous agents (including bug bounty, CTF solving, CVE intelligence and exploit generation), and a visual engine with dashboards and vulnerability cards.

The README groups 150+ security tools by area: network (25+), web application (40+), cloud (20+), binary (25+), CTF (20+) and OSINT (20+), with process management, smart caching and error recovery behind them. Installation is a git clone and `pip3 install -r requirements.txt`, then pointing an MCP client at the server. The README's own Legal and Ethical Use section limits use to authorised penetration testing with written permission and security research on systems you own or are authorised to test, and warns against unauthorised testing, malicious activity and data theft.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-17.

License
MIT
Latest release
No GitHub releases
Last commit
2026-08-03
Contributors
2
Forks
2,696
Open issues and PRs
117
First published
2025-07-10

Source: GitHub, npm and PyPI public APIs.

#AI#Cybersecurity#Penetration Testing#Multi-Agent Systems#Automation#Web Browsing
$ Install
$ git clone https://github.com/0x4m4/hexstrike-ai.git
↗ Visit site★ GitHub
01

Features

01Over 150 professional security tools for diverse assessments.
0212+ autonomous AI agents for specialized cybersecurity tasks.
03Intelligent decision engine for optimal testing strategies and adaptation.
04Multi-agent architecture enabling collaborative and comprehensive operations.
05Modern visual engine for real-time dashboards and vulnerability reporting.
02

Why choose it

+Brings a very broad set of security tools (150+) behind a single MCP interface for AI agents.
+Organised by domain (network, web, cloud, binary, CTF, OSINT), which makes tool coverage easy to see.
+Includes agent roles such as CTF solver and CVE intelligence, plus caching and error recovery for long scans.
+MIT licensed, and the README states clear legal and ethical use rules.
03

Trade-offs

!This is dual-use offensive tooling: use it only on systems you own or have written authorisation to test, as the README itself stresses.
!The underlying tools must be installed separately, so a working setup needs many external security tools, not just the Python server.
!The README notes that LLMs often refuse blunt penetration-testing requests, so results depend on how the model is prompted, and autonomous agents need careful supervision.
05

Maintenance check

ActiveChecked: 2026-10-25
Last commit
2026-08-03
Commits, last 90 days
1
Releases, last 90 days
0
Latest release
—
Open issues
125
Recent issues with at least one comment
4/19
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #32 Hexstrike on MacBook Pro M4 - Mac OS Tahoe 2614 comments · 2025-08-23
  • #12 Tools Installation Scripts11 comments · 2025-08-16
  • #116 antigravity mcp problem7 comments · 2025-12-13
  • #124 Vulnerability Report: Remote Code Execution (RCE) via Command Injection6 comments · 2025-12-26
  • #119 Too many mcp tools .Can we disable some tools?6 comments · 2025-12-18

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You conduct automated penetration testing, bug bounty recon, or security audits and want AI agents to orchestrate 150+ professional cyber tools.
  • You want to bridge LLMs with real offensive security workflows covering network scanning, web exploitation, cloud security, and OSINT.
Look elsewhere if
  • You do not have explicit written authorization on target networks (strictly respect legal and ethical penetration testing policies).
  • Your focus is purely binary reverse engineering and decompilation (ghidra-mcp or ida-pro-mcp are purpose-built for reversing).
06

How it differs

ghidra-mcp logovs ghidra-mcp★ 5.9k

hexstrike-ai covers end-to-end network pentesting, scanning, and web exploitation; ghidra-mcp is focused strictly on binary decompilation.

Full comparison →
agentic_security logovs agentic_security★ 2.0k

hexstrike-ai automates classic offensive network/web pentesting; agentic_security tests LLMs themselves against prompt injection and jailbreaks.

Full comparison →
07

Compatibility

MCP Protocol
Native MCP Support
Verified via docs
Claude Desktop
Supported
Verified via docs
VS Code Copilot
Supported
Verified via docs
Cursor
Supported
Verified via docs
Roo Code
Supported
Verified via docs
5ire
Warning (v0.14.0 not supported)
Verified via docs
08

Quick start

1
$ git clone https://github.com/0x4m4/hexstrike-ai.git
09

Use cases

↳Automated penetration testing and security assessments.
↳Support for bug bounty hunting and vulnerability discovery.
↳Assistance in Capture The Flag (CTF) challenges.
10

Alternatives

⚡Top VS:
VSghidra-mcp★5.9k→VSagentic_security★2.0k→VSCyberStrike★3.3k→VShexstrike-ai-community-edition★155→
ghidra-mcp logo
ghidra-mcp★ 5.9k
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.
VSCompare→
agentic_security logo
agentic_security★ 2.0k
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
VSCompare→
CyberStrike logo
CyberStrike★ 3.3k
Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK, OWASP WSTG, CIS Benchmarks. Post-exploit: Linux/Windows/macOS/AWS/Azure/K8s/CI-CD. Web UI + Cloudflare Tunnel. Your AI red team.
VSCompare→
hexstrike-ai-community-edition logo
hexstrike-ai-community-edition★ 155
HexStrike AI Community Edition - Cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
VSCompare→
awesome-n8n-templates logo
awesome-n8n-templates★ 26.1k
Supercharge your workflow automation with this curated collection of n8n templates! Instantly connect your favorite apps-like Gmail, Telegram, Google Drive, Slack, and more-with ready-to-use, AI-powered automations. Save time, boost productivity, and unlock the true potential of n8n in just a few clicks.
VSCompare→
ai-security-tool logo
ai-security-tool★ 1.2k
🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI.
VSCompare→
Viper logo
Viper★ 5.3k
Adversary simulation and Red teaming platform with AI
VSCompare→
context-space logo
context-space★ 813
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
VSCompare→
See all alternatives →

Featured in these lists

  • Open-Source Security Tools for MCP Servers and AI Agents

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
0x4m4 /
hexstrike-ai
↗

MCP framework that gives AI agents 150+ penetration-testing tools

13.1k2.7kMIT
Last commit2mo ago
StatusActive
CategorySecurity & Safety
Contributors2
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.