AUTOMATIONSWITCH
CommunitySecurity

HexStrike AI

by 0x4m4 (community)

Advanced MCP server that lets AI agents perform offensive security tasks and red-team workflows. 8,695 GitHub stars and 1 commit on main in the last 30 days.

8,695·6 tools·Released JUN 2025·MIT
pip install hexstrike-ai
Share:

Advanced MCP server that lets AI agents perform offensive security tasks and red-team workflows. 8,695 stars and 1 commit on main in the last 30 days.

Reviewed by M. Nouriel · MAY 2026

INSTALL THIS SERVER

{ "mcpServers": { "hexstrike": { "command": "python", "args": [ "-m", "hexstrike_ai" ] } } }
PrereqPyPI: `hexstrike-ai`. Use ONLY within explicit written authorisation; offensive security operations against systems you do not own may violate the law. Path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS).
{ "mcpServers": { "hexstrike": { "command": "python", "args": [ "-m", "hexstrike_ai" ] } } }
{ "mcpServers": { "hexstrike": { "command": "python", "args": [ "-m", "hexstrike_ai" ] } } }
{ "mcpServers": { "hexstrike": { "command": "python", "args": [ "-m", "hexstrike_ai" ] } } }
{ "mcpServers": { "hexstrike": { "command": "python", "args": [ "-m", "hexstrike_ai" ] } } }

6 TOOLS AVAILABLE

run_recon
Run reconnaissance against a target (domain, IP, asset)
Admin
scan_target
Scan a target for known vulnerabilities
Admin
list_findings
List findings with severity and CVE references
Read
generate_report
Generate a security assessment report
Read
list_techniques
List available offensive-security techniques (MITRE ATT&CK aligned)
Read
plan_engagement
Plan a red-team engagement based on target and scope
Admin

OUR ASSESSMENT

Strengths
  • 8,695 GitHub stars.
  • 1 commit on main in the last 30 days.
  • MIT license.
  • MITRE ATT&CK aligned technique catalog.
  • End-to-end workflow from recon to reporting.
Weaknesses
  • Offensive-security tooling carries legal risk if used outside authorised engagements.
  • 1 commit/30d is at the bottom of the strict gate.
  • Community-maintained; no commercial security backing.
Security Notes

HexStrike AI executes offensive-security techniques. Use ONLY within explicit written authorisation (engagement letter, bug bounty program scope, your own infrastructure). Running against systems you do not own or have permission to test may violate the Computer Fraud and Abuse Act (US), Computer Misuse Act (UK), and similar laws worldwide. Agents that orchestrate HexStrike must include scope enforcement in the prompt path.

Best For

Authorised penetration testers running red-team engagements; security researchers studying offensive techniques; bug bounty hunters automating recon and triage within program scope.

TECHNICAL DETAILS

Language
python
Transport
stdio
Clients
Claude DesktopClaude CodeCursorVS CodeWindsurf
License
MIT
GitHub
0x4m4/hexstrike-ai · ★ 8,695
npm
hexstrike-ai
Last Release
hexstrike-ai (PyPI latest)MAY 12, 2026
First Released
JUN 1, 2025

ADOPTION METRICS

// GitHub Stars
8,695

// Reading this8,695 stars on 0x4m4/hexstrike-ai. 1 commit on main in the last 30 days.

// Popularity Rank
#4
Globally · #4 in Security

// Reading thisPairs with Prowler, Trivy, CrowdStrike Falcon, Snyk Agent Scan, Auth0, AWS IAM, AWS CloudTrail, HashiCorp Vault, Infisical, Okta in security. HexStrike owns the offensive-security slot.

SOURCES & VERIFICATION

We don't take any single directory's word for it. Before scoring, we cross-reference 4 public MCP sources, install the server ourselves against the clients we cover, and record when we last re-verified.

01
Discovered
Manual submission
First indexed MAY 12, 2026
02
Cross-referenced
4 directories
PulseMCP, MCP.so, Glama, Smithery
03
Verified against
Claude Desktop, Cursor
Installed and tested across clients
04
Last re-checked
MAY 12, 2026
Weekly re-verification
// How other directories see it

The same server, 4 different lenses. We reconcile these signals into our editorial score, which is why our number sometimes diverges from a directory-aggregate star count.

SourceTheir ratingTheir star countTheir downloadsLast synced
AutomationSwitch This page4.3editorial8,695MAY 12, 2026
PulseMCP— unratedunavailableunavailableMAY 12, 2026
MCP.so— unratedunavailableunavailableMAY 12, 2026
Glama— unratedunavailableunavailableMAY 12, 2026
Smithery— unratedunavailableunavailableMAY 12, 2026

// Counts are directory-reported; we don't adjust them. Discrepancies usually come from different snapshot times or star-caching.

OTHER SECURITY MCP SERVERS

Vendor4.6

Prowler MCP

Prowler

Cloud Security Posture Management (CSPM) platform with 1000+ security checks across multiple cloud providers and 70+ compliance frameworks, exposed through MCP. Three deployment options: Prowler Cloud (recommended), local stdio, self-hosted HTTP. 13,717 stars, Apache-2.0.

8 tools13,717
Official4.5

Snyk Agent Scan

Snyk

Snyk's security scanner for AI agents, MCP servers, and agent skills. Scans MCP server manifests and agent skill files for known security risks. 2,366 GitHub stars and 81 commits on main in the last 30 days.

6 tools2,366
Official4.4

CrowdStrike Falcon MCP

CrowdStrike

Official CrowdStrike Falcon MCP server. Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting. 148 stars and 8 commits on main in the last 30 days.

7 tools148
Vendor4.3

Auth0 MCP Server

Auth0

Official Auth0 MCP server connecting Claude, Cursor, Windsurf, VS Code, and Gemini to Auth0 Management APIs. Create apps, deploy Actions, debug logs, and query users with natural-language commands. Read-only mode and tool-glob filtering supported. Beta software per Auth0.

8 tools106
Official4.2

HashiCorp Vault MCP

HashiCorp

Official HashiCorp MCP for Vault: secrets, mounts, KV, and PKI management with stdio and Streamable HTTP transports. 9 commits on main in the last 30 days. MPL-2.0 with HashiCorp official-vendor signal.

9 tools45
Official4.1

AWS IAM MCP

AWS Labs

Official AWS Labs MCP for IAM administration: users, roles, groups, policies, inline policies, access keys, and policy simulation. Read-only mode supported via --allow-write opt-in pattern. Apache-2.0 within awslabs/mcp monorepo.

7 tools8,924
// Get in touch

DISCUSS YOUR
MCP REQUIREMENTS.

Evaluating a server, scoping an internal deployment, or working out whether MCP is the right fit at all. Start the conversation and we will point you at the right piece of the ecosystem.

Discuss Your MCP Requirements →