hexstrike-ai
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.
Runssource: GitHubhomepagePythonMITcommit d689933ff579
Python, MIT licensed. The project labels itself: 0x4m4, ai, ai agents, ai cybersecurity, ai hacking, ai penetration testing, ai security tool and artificial intelligence.
hexstrike-ai runs. An Argusic agent installed it in 31 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
HexStrike AI MCP Server v6.0 starts on any port, serves Flask API with 30+ endpoints including command execution, file management, intelligence analysis, process management, caching, and telemetry. FastMCP client connects and registers 16+ security tools.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 94.7 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pip3 not installed in base Python2 minutes
- PEP 668 externally-managed environment blocked pip install1 minute
- Install time
- 31 minutes
- Cold machine to finish
- 34 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- Model tokens used
- 642,859
- Exact commit tested
- d689933ff579
- Container image
- sha256:4c3d41857be3
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Verified endpoints:** `/health`, `/api/command`, `/api/files/list`, `/api/intelligence/analyze-ta…
**MCP client:** Starts and connects to the server via FastMCP protocol.
**Errors encountered:**
1. `pip3` not installed → fixed by running `python3 /tmp/get-pip.py` (2 min)
2. Externally-managed environment (PEP 668) → fixed by `--break-system-packages` (1 min)
3. Health endpoint slow (127 `which` commands) → not a bug, just slow; works within 1.5-2s (no fix …
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 3…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 31, "errors": [{"msg": "pi…
tokens used
642,859Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 31 minutes.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Runs with mocks | 92.00 | 0.07 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.07 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.18 |
Topics (from GitHub)
0x4m4aiai-agentsai-cybersecurityai-hackingai-penetration-testingai-security-toolartificial-intelligencectf-toolsgenerative-aihexstrikekali-linuxkali-toolsllmllm-integrationmcpmcp-servermcp-toolspentestingpentesting-tools
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/hexstrike-ai)Questions
- Does hexstrike-ai run?
- Yes. hexstrike-ai runs. Argusic installed and launched it on a clean machine in 31 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test hexstrike-ai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d689933ff579. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test hexstrike-ai?
- The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does hexstrike-ai take to install?
- 31 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does hexstrike-ai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing hexstrike-ai?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for hexstrike-ai?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.