HexStrike AI
open-sourceThe section your link pointed to isn't on HexStrike AI's page any more, so we've brought you to the top.
AI-powered MCPMCPModel Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. penetration testing platform integrating 150+ cyber tools and 12+ autonomous AI agents for automated security assessments.
Summary
HexStrike AI is an open-source penetration testing platform, licensed under MIT, that runs as an MCP server connecting AI agents to a library of over 150 cybersecurity tools so they can plan and execute security assessments autonomously rather than waiting on manual invocation for each step. It is started as a server process on a host or in debug mode on a custom port, and its 12-plus autonomous agents handle tasks like reconnaissance and vulnerability discovery within that running instance. The design targets red teamers and offensive security practitioners who want an AI layer orchestrating existing tooling instead of running each utility by hand, placing it in the emerging space of AI-driven offensive security frameworks rather than any single named competitor. It is a young project, first committed in 2025 with three contributors and about a dozen commits over the past year, so activity is present but still light.
AI-powered MCP penetration testing platform integrating 150+ cyber tools and 12+ autonomous AI agents for automated security assessments.
How HexStrike AI helps
Which entry points into a target would an attacker's automated recon turn up first?
the reconnaissance agents chain scanning and enumeration tools against the target and report back the exposed services and paths they found, in the order the agents pursued them
Which of my exposed services carry known vulnerabilities worth chasing?
the vulnerability discovery agents match what recon turned up against known weaknesses and hand back a prioritized list rather than a raw tool dump
How far could an attacker get through my systems without a person driving each step?
the agents plan and execute a multi-stage assessment across the tool library on their own within the running instance, chaining recon into exploitation attempts instead of waiting on a manual command for each stage
Which of my hosts justify a closer manual look after an automated pass?
the running instance works through the target with its full tool set and surfaces the findings it judged worth reporting, letting a practitioner start from that shortlist instead of the whole surface
Do I have the same tool coverage across two separate assessments?
both runs draw on the same library of over 150 tools inside the server instance, so a comparison of their output reflects differences in the target rather than differences in what each run had available to it
Languages
Command line
| option | found in | since | description |
|---|
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Score card
-
Shipping velocity releases a month, last 12 months
-
Documentation quality release-notes rubric, 0–100
-
Breaking-change discipline how rarely a release breaks users, and notice given
-
Maintenance risk quiet time against its own cadence, maintainers
-
Innovation & surface new capabilities, API and MCP surface
- Community health
-
Contributor trend distinct committers, this year against last
-
Maintainer concentration bus factor now against a year ago
-
Issue backlog trend issues closed per issue opened, 12 months
-
Responsiveness median time to a maintainer’s first reply
Nine scores for HexStrike AI, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.
Score cards are part of every paid plan.
See plans → Already subscribed? Sign in →Trajectory
Blank means never measured; nothing here is a filled-in zero.
Peer standings are included with Researcher and Business. See how this tool ranks against its competitors, using data we don't publish anywhere else.
See plans →Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.
How this is scored
- Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
- Documentation quality — the release-notes rubric published on the analytics page, unchanged.
- Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
- Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
- Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
- Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
- Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
- Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.
Release-note detail over time
See how much detail HexStrike AI puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.
Checking release-note history…
Releases
Nothing shipped since we started watching. Releases and docs updates land here as they happen.
Project health
Issue, contributor and maintainer activity in 0x4m4/hexstrike-ai, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 3 +1 vs prior 12 months
- Maintainers 0 +0 joined · −1 left, last 12 months
- Bus factor 0 committers behind half the commits
- Community-filed 100% of issues opened, last 12 months
- Median time to close 2.1 days first maintainer reply 24 hours
- Open backlog 65 of 127 issues ever filed
- Issues opened / month 5 · 0 communitymaintainers
- Open backlog 65
- Contributors / month 0
- Commits / month 0
- Stars 11,942
- other 100%
Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this
Articles
1 article · updated Nov 4, 2026Where HexStrike AI turns up in what others publish: how-tos, attack reports that name it, and incident write-ups. A row says why it is here and quotes where the article names it; the link goes to the publisher.
Tutorials & guides 1
-
AI-Powered Active Directory Pentesting with Claude, HexStrike AI & NetExec
We wire the HexStrike AI MCP server into Claude Desktop and let the model operate NetExec on our behalf: you ask for a technique in English, the AI picks the right module, builds the command, runs it, and returns…
2 more quotes
Once Claude Desktop connects to the HexStrike AI server, the model acts as your operator: it reads your plain-English request, selects the right tool and module, fills in the flags, runs the command, and explains the…
If you have not installed and connected HexStrike AI yet, the first three sections below cover the full setup.
Libraries its release ships
What its latest release locks, checked against known advisories.We can only check tools that publish GitHub releases.
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.
Choose a badge style and copy the code →