Our take
Maintaineda few commits in the last 90 days- Activity
- 28
- Community
- 12
- Issues
- 39
- Pull requests
- 20
+785 stars in the last 30 days
- Fewer contributors than 86% of the projects we track
HexStrike AI offers a broad MCP-based interface for security workflows, but its recent maintenance record and highly concentrated contributor base call for careful evaluation before relying on it.
Good fit if
- You already use Python and an MCP-compatible AI client, and want to experiment with agent-assisted security assessments.
- Your work is authorized testing, CTFs, or research, and you can install and manage the underlying security tools.
- You can review and supervise tool execution, including commands that may affect remote systems.
Look elsewhere if
- You need evidence of active release cadence or a broader maintainer base: there has been no release in the past year, and most of the code comes from one person.
- You require a project with automated tests or CI documented in its repository data.
- You want an out-of-the-box deployment that avoids installing Python dependencies and external security tools.
All health signals
| Last commit | 2026-08-03 (2 months ago) |
|---|---|
| Commits, last 90 days | 1 |
| Releases, last 12 months | 0 |
| Contributors | 2 (top contributor: 98% of commits) |
| Issues closed, last 90 days | 3 (typically closed in 42 days) |
| Pull requests merged, last 90 days | 0 |
| Project age | 15 months |
Checked on 2026-10-14 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
13,703Forks
2,793Change since Nov 17, 2026: +36 stars·+15 forks
Overview
HexStrike AI is a Python MCP server that lets compatible AI agents interact with cybersecurity tools for penetration testing, vulnerability discovery, bug bounty work, and security research. It aims to bridge language models and existing command-line tools with a decision engine and specialized workflows.
This is most useful when a security practitioner wants an AI client to help coordinate authorized assessments across different tool categories. It is an integration layer, not a replacement for the underlying tools or the judgment needed to scope and supervise testing.
Key Features
- Exposes security tool workflows to MCP-compatible clients, with setup examples for Claude Desktop, Cursor, and VS Code Copilot.
- Describes support for more than 150 tools across network, web, cloud, binary analysis, CTF, and OSINT tasks.
- Includes decision and parameter-optimization components intended to help select tools for a target.
- Provides named workflows and agents for bug bounty tasks, CTFs, CVE intelligence, and vulnerability correlation.
- Offers HTTP endpoints for health checks, target analysis, tool selection, telemetry, and process management.
- Documents caching, process monitoring, and a browser agent using headless Chrome.
Use Cases
- A penetration tester with written authorization can connect an MCP client and use it to coordinate reconnaissance and vulnerability checks.
- Bug bounty researchers can use the documented workflow manager and web reconnaissance tools within a program's defined scope.
- CTF participants can connect an AI client to the listed binary analysis, forensics, and challenge-solving tools.
- Security teams assessing cloud or container configurations can use the documented integrations for tools such as Prowler, Trivy, and Kubernetes security checks.
What you need
Detected in the repository
- Python (from requirements.txt)
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
The README's basic setup uses Python and a virtual environment:
git clone https://github.com/0x4m4/hexstrike-ai.git
cd hexstrike-ai
python3 -m venv hexstrike-env
source hexstrike-env/bin/activate
pip install -r requirements.txt
python3 hexstrike_server.py
See the README for MCP client configuration, tool installation, and server options.
Considerations
- The project can invoke powerful security utilities, including tools for scanning and exploitation. Run it in an appropriate environment, restrict targets to authorized scope, and supervise agent activity.
- The README lists numerous external tools as integrations; installing the Python requirements alone does not establish that those tools are present or configured.
- Repository health data reports just one commit in the last 90 days, no release in the past year, and no merged pull requests in that period. Three issues were closed in the last 90 days, with a median closure time of 42 days.
- The contributor base is small and concentrated, with nearly all recorded contributions attributed to one person. The repository data also reports no CI or tests, which may make regressions harder to catch.
- The README describes a forthcoming v7.0 with Docker support, but the available project data does not show Docker configuration. Do not assume that planned feature is available in the current setup.
Found this useful?
Share it with someone who would like hexstrike-ai.