strix
Integrates with GitHub Actions and CI/CD pipelines to automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Strix
The open-source AI pentesting tool. Autonomous AI hackers that find and fix your app’s vulnerabilities.
New! Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - Get started with no setup required.
Strix Overview
Strix are autonomous AI penetration testing agents that act just like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proofs-of-concept. Built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools.
Key Capabilities:
Full pentesting toolkit - reconnaissance, exploitation, and validation out of the box
Multi-agent orchestration - teams of AI pentesters that collaborate and scale
Real exploit validation - working PoCs, not false positives like legacy vulnerability scanners
Developer‑first CLI - actionable findings with remediation guidance
Auto‑fix & reporting - generate patches and compliance-ready pentest reports
Related MCP server: Kali MCP Server
Use Cases
Application Security Testing - Detect and validate critical vulnerabilities in your applications
Rapid Penetration Testing - Get penetration tests done in hours, not weeks, with compliance reports
Bug Bounty Automation - Automate bug bounty research and generate PoCs for faster reporting
CI/CD Integration - Run tests in CI/CD to block vulnerabilities before reaching production
🤖 Agentic Mode (Antigravity & OpenCode — no LLM keys for Strix)
Run Strix's full pentest muscle directly out of Google Antigravity or OpenCode: the agent
(the model you already configured in your IDE) becomes the pentest brain, and Strix's Kali sandbox is
exposed as its hands over MCP. Strix itself needs zero API keys — nmap, sqlmap, ffuf,
chromium and friends run in the sandbox container, driven by plain MCP tool calls.
One-command setup
powershell -ExecutionPolicy Bypass -File setup.ps1 -SeedTestSiteThat script verifies Docker, creates the Python venv, pulls the sandbox image
(ghcr.io/usestrix/strix-sandbox), registers the MCP server in both Antigravity's .agents/mcp_config.json
and OpenCode's opencode.json, and (with -SeedTestSite) starts a legal local pentest target
(OWASP Juice Shop) on http://localhost:4321.
Run a scan
Open this folder in Google Antigravity IDE or OpenCode and type:
/runscan http://localhost:4321The runscan / pentest agent (.agents/skills/runscan/SKILL.md in Antigravity or .opencode/agents/pentest.md in OpenCode) will:
health-check the sandbox (
strix_sandbox_health/sandbox_health),read or derive the shared threat model, then recon and map the target (
strix_sandbox_exec: nmap, curl, httpx, katana...),create its own account through the real UI (
strix_browser→ Chromium) if the app requires one, using throwaway credentials, and a second one for access-control tests,test in priority order (authz → injection → business logic → client-side), capturing every exchange through the engine proxy (
strix_proxy_view_request), recording coverage as it goes, and filing only confirmed findings (strix_report_finding),reconcile the coverage ledger, then write
strix_runs/runscan-*/penetration_test_report.mdand hand you a summary.
Prefer the terminal? The same run works headlessly:
./scripts/runscan-agent.ps1 -Target https://staging.example.com -Mode standardscripts/runscan-agent.sh https://staging.example.com standardHow the pieces fit
Antigravity / OpenCode Agent this repo / MCP Docker
──────────────────────────── ─────────────── ──────
/runscan <target> ─► pentest agent ─► strix_sandbox_exec ─► Kali sandbox container
(brain, no keys) strix_browser (nmap, sqlmap, chromium,
strix_proxy_* Caido proxy...)
strix_coverage_*
strix_report_finding
strix_finish_report ─► strix_runs/runscan-*/report.mdThe MCP server exposes 37 tools: the sandbox and browser, the Caido proxy (history, raw view, replay, sitemap, scope), the 65 engine skill packs, notes, todos, the coverage ledger, the threat model, and the full finding lifecycle. All of them are thin wrappers over the shipped engine code — the only part of Strix replaced by the host agent is the model itself.
Two agents, one engine
/runscan <target> [mode]→pentest: drives Strix's own Kali toolbelt./runz4nzu <target> [mode]→Z4nzu: selects real tools from the Z4nzu/hackingtool catalog, installed from a pinned commit into the same sandbox at runtime and queried live (v3.1.0 reports 263 entries across 22 collections; the registry, not the README's 219, is the truth). Same authorization gate, evidence bar, coverage ledger and Strix reporting; different tool selection. It never invents a tool or command, never uses hackingtool's own AI layer — the host agent is the brain — and never treats the catalog's/findoutput as vetted. DDOS, phishing, wireless capture, RAT/persistence and credential-capture categories are excluded by default even though entries exist.
Files: mcp/server.py (MCP stdio server), mcp/smoke_test.py (parity check —
runs without Docker, --with-sandbox includes the container),
mcp/install_mcp.py (registers the server with OpenCode and Antigravity),
.opencode/agents/pentest.md + .opencode/agents/Z4nzu.md (OpenCode brains),
.opencode/agents/strix-*.md (recon, web, API, validation and report subagents),
.opencode/commands/runscan.md + runz4nzu.md (slash commands),
scripts/runscan-agent.{ps1,sh} (headless runners),
.agents/skills/runscan/SKILL.md + .agents/mcp_config.json (Antigravity).
The parity matrix, including what is host-owned rather than engine-owned, is in
docs/integrations/agentic-mode.mdx.
Point it at your own site only when you are authorized to test it.
🚀 Quick Start
Prerequisites:
Docker (running)
An LLM API key from any supported provider (OpenAI, Anthropic, Google, etc.)
Installation & First Scan
# Install Strix
curl -sSL https://strix.ai/install | bash
# One-time guided setup: pick a model, paste your key (masked), verify the
# connection, and everything is saved for every future run
strix setup
# Run your first security assessment — URL, directory, or code
strix --target https://your-app.comNo env exports or config files required: strix setup writes
~/.strix/cli-config.json, and future scans are a single command. Prefer the
explicit form (great for CI)? Set everything on the command line:
strix --target ./app-directory --llm "openrouter/z-ai/glm-5.3" --api-key "your-api-key"While a scan runs, a live dashboard in your terminal shows every agent, what it is doing right now, the shared plan (steps remaining), findings as they are filed, and tokens/cost so far.
Free-tier providers run out of quota mid-scan? Add a failover chain in the
same strix setup pass (or re-run it): when the main provider hits a wall,
Strix switches to the next backup automatically and keeps scanning. See
Free-quota failover chain below.
First run automatically pulls the sandbox Docker image in the background
while verifying your LLM connection. Results are saved tostrix_runs/<run-name>
Updating
# Self-update the standalone binary to the latest release
strix --update
# ...or re-run the installer
curl -sSL https://strix.ai/install | bashInstalled with pipx, uv, or pip? strix --update prints the matching upgrade command instead (pipx upgrade strix-agent, uv tool upgrade strix-agent, pip install --upgrade strix-agent). Strix also shows a notice with the right command when a new version is available.
Ways to Run Strix
Open Source - free, runs locally with Docker and your own LLM key. Quick Start
Strix Cloud - no setup, validated findings, one-click autofix, and PR reviews. Run a pentest →
Enterprise - SSO, compliance-ready reports, VPC or self-hosted deployment. Try Strix Enterprise →
☁️ Strix Cloud
Try the Strix full-stack penetration testing platform at app.strix.ai - sign up for free, connect your repos and domains, and launch a pentest in minutes.
Validated findings with PoCs - every vulnerability includes a working proof-of-concept exploit and reproduction steps
One-click autofix - AI-generated security patches as ready-to-merge pull requests
Continuous pentesting - always-on vulnerability scanning that keeps pace with your deployments
DevSecOps integrations - GitHub, GitLab, Bitbucket, Slack, Jira, Linear, and CI/CD pipelines
Continuous learning - AI that builds on past findings, adapts to your codebase, and reduces false positives over time
🏢 Enterprise
Get the same Strix experience with enterprise-grade controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support and SLA, custom deployment options (VPC or self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment.
🤖 Use Strix from Your Coding Agent
Strix is agent-ready. Give Claude Code, Cursor, Codex, or any SKILL.md-compatible agent the ability to run pentests, fix findings, and set up CI scanning:
npx skills add usestrix/strixThis installs nine skills for running pentests, fixing findings, and CI scanning, against code, web apps, APIs, and the OWASP Top 10. Agents can use the local CLI or the managed cloud with the same engine.
See AGENTS.md for the quick reference, docs.strix.ai/llms.txt for the CLI, and docs.app.strix.ai for the API.
✨ Features
Agentic Pentesting Tools
Strix agents come equipped with a comprehensive offensive security toolkit - the same tools used by professional penetration testers and ethical hackers:
HTTP Interception Proxy - Full request/response manipulation and analysis with Caido
Browser Exploitation - Automated browser for testing XSS, CSRF, clickjacking, and auth bypass flows
Shell & Command Execution - Interactive terminal for exploit development and post-exploitation
Custom Exploit Runtime - Python sandbox for writing and validating proof-of-concept exploits
Reconnaissance & OSINT - Automated attack surface mapping, subdomain enumeration, and fingerprinting
Static & Dynamic Code Analysis - SAST + DAST capabilities for comprehensive application security testing
Vulnerability Knowledge Base - Structured findings with CVSS scoring and OWASP classification
Comprehensive Vulnerability Scanner
Strix identifies, validates, and exploits a wide range of security vulnerabilities across the OWASP Top 10 and beyond:
Broken Access Control - IDOR, privilege escalation, auth bypass
Injection Attacks - SQL injection, NoSQL injection, OS command injection, SSTI
Server-Side Vulnerabilities - SSRF, XXE, insecure deserialization, RCE
Client-Side Attacks - XSS (stored/reflected/DOM), prototype pollution, CSRF
Business Logic Flaws - Race conditions, payment manipulation, workflow bypass
Authentication & Session - JWT attacks, session fixation, credential stuffing vectors
Infrastructure & Cloud - Misconfigurations, exposed services, cloud security issues
API Security - Broken authentication, mass assignment, rate limiting bypass
Graph of Agents (Multi-Agent Pentesting)
Advanced multi-agent orchestration for comprehensive automated penetration testing:
Distributed Pentesting - Specialized AI agents for recon, exploitation, and post-exploitation
Scalable Security Testing - Parallel execution across multiple targets for fast, comprehensive coverage
Dynamic Coordination - Agents share discoveries, chain vulnerabilities, and collaborate like a red team
🖥️ Local Web Viewer
Every scan writes its results to disk as it runs. Bring them up in a local dashboard with a single command:
# Open the most recent run
strix view
# ...or open a specific run by name
strix view my-run-name
# Expose the viewer on all IPv4 interfaces at a fixed port
strix view --host 0.0.0.0 --port 8080 --no-openThe dashboard shows the findings, a live map of the agent team, and past runs. Nothing leaves your machine, and the UI ships prebuilt. strix view binds to 127.0.0.1 and prints a tokened link that grants access to the run, so share it carefully.
See the viewer documentation for the options and for reaching the viewer from another machine.
Usage Examples
Basic Usage
# Scan a local codebase
strix --target ./app-directory
# Security review of a GitHub repository
strix --target https://github.com/org/repo
# Black-box web application assessment
strix --target https://your-app.comAPI Testing (OpenAPI / Swagger / Postman)
Point Strix at an API contract and it tests every declared endpoint instead of having to discover them by crawling. Pair the spec with the live base URL so the agent knows where to send traffic:
# OpenAPI / Swagger file, Postman export, or a live collection by id
strix --target ./openapi.yaml --target https://api.your-app.com
strix --target postman://<collection-uuid> --target https://api.your-app.comAdvanced Testing Scenarios
# Grey-box authenticated testing
strix --target https://your-app.com --instruction "Perform authenticated testing using credentials: user:pass"
# Multi-target testing (source code + deployed app)
strix -t https://github.com/org/app -t https://your-app.com
# Targets from a file, one target per non-empty, non-comment line
strix --target-list ./targets.txtSee the CLI reference for every option, including scan modes, diff scope, instruction files, and budgets.
Headless Mode
Run Strix programmatically without interactive UI using the -n/--non-interactive flag - perfect for servers and automated jobs. The CLI prints real-time vulnerability findings and the final report before exiting. Exits with non-zero code when vulnerabilities are found.
strix -n --target https://your-app.comCI/CD (GitHub Actions)
Strix can be added to your pipeline to run a security test on pull requests with a lightweight GitHub Actions workflow:
name: strix-penetration-test
on:
pull_request:
jobs:
security-scan:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Install Strix
run: curl -sSL https://strix.ai/install | bash
- name: Run Strix
env:
STRIX_LLM: ${{ secrets.STRIX_LLM }}
LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
run: strix -n -t ./ --scan-mode quickIn CI pull request runs, Strix automatically scopes quick reviews to changed files, which is why the checkout above fetches full history. See theCI/CD documentation for the details.
Configuration
export STRIX_LLM="openrouter/z-ai/glm-5.3"
export LLM_API_KEY="your-api-key"
# Optional
export LLM_API_BASE="your-api-base-url" # if using a local model, e.g. Ollama, LMStudioStrix automatically saves your configuration to~/.strix/cli-config.json, so you don't have to re-enter it on every run.
See the configuration reference for every environment variable.
Free-quota failover chain
A scan can outlive a provider's free quota. Configure sticky failover backups so the scan continues on the next provider instead of stopping:
strix setup # answer "y" to "Set up a failover chain?" and paste the backup keysPresets cover
gemini/gemini-2.5-flash(AI Studio free tier) andgroq/llama-3.3-70b-versatile(Groq free tier); option 3 accepts any OpenAI-compatible endpoint (custom base URL), e.g.https://api.tokenrouter.com/v1.Every entry is verified with one real round-trip before it is saved; dead keys are dropped.
A provider is switched away from when it keeps rate-limiting (3 consecutive failures inside 5 minutes) or immediately on an auth/billing error. The switch is sticky for the rest of the scan and the dashboard prints it live.
The chain resets on the next run, so the primary is retried first again.
Equivalent env/config form (STRIX_FALLBACK_LLMS, saved to
~/.strix/cli-config.json by the wizard):
export STRIX_FALLBACK_LLMS='[{"model": "gemini/gemini-2.5-flash", "api_key": "your-key"}, {"model": "groq/llama-3.3-70b-versatile", "api_key": "your-key"}]'Sign in with a ChatGPT subscription
Instead of a metered API key, you can run Strix on your ChatGPT Plus/Pro subscription:
strix auth login chatgpt # sign in with your ChatGPT account
export STRIX_LLM="chatgpt/gpt-5.4" # chatgpt/<model> runs on the subscription
strix auth status # show the active sign-in, or logout to forget itUse the managed platform: strix cloud
Run scans on app.strix.ai from the terminal, without Docker or an LLM key:
strix cloud login # browser sign-in, one credential per install
strix cloud scans start --source . --yes --wait # scan local code, approving the upload
strix cloud scans start --engagement-type live_test --domain-ids <uuid> --wait
strix cloud vulns list --severity criticalEvery REST API operation has a matching strix cloud <resource> <verb> command. Run strix cloud to list the resources, and add help to a resource to list its verbs. Output is JSON when stdout is not a terminal or when you pass --json. Binary downloads are the exception: redirect the raw bytes, or combine --output FILE --json for download metadata.
See the cloud CLI documentation for scopes, workspaces, billing, and source-upload options.
Connect your own MCP servers
Strix can connect to Model Context Protocol (MCP) servers you list and expose their tools to the agent during a run. Create ~/.strix/mcp-servers.json with a JSON list of local stdio servers or remote http servers:
[
{
"name": "github",
"transport": "http",
"url": "https://api.githubcopilot.com/mcp/",
"auth": { "kind": "bearer", "token": "your-token" },
"allowed_tools": ["list_issues"]
}
]Each server's tools are namespaced by name, for example github_list_issues. See the MCP documentation for the full schema, tool filtering, and stdio servers.
Recommended models for best results:
Z.ai GLM-5.3 on OpenRouter -
openrouter/z-ai/glm-5.3(the default pick)OpenAI GPT-5.4 -
openai/gpt-5.4Anthropic Claude Sonnet 4.6 -
anthropic/claude-sonnet-4-6Google Gemini 3 Pro Preview -
vertex_ai/gemini-3-pro-previewDeepSeek V4 Pro -
deepseek/deepseek-v4-proMoonshot Kimi K3 -
moonshot/kimi-k3
See the LLM Providers documentation for all supported providers including Vertex AI, Bedrock, Azure, and local models.
Documentation
Full documentation is available at docs.strix.ai - including detailed guides for usage, CI/CD integrations, skills, and advanced configuration.
Contributing
We welcome contributions of code, docs, and new skills - check out our Contributing Guide to get started or open a pull request/issue.
Join Our Community
Have questions? Found a bug? Want to contribute? Join our Discord!
Support the Project
Love Strix? Give us a ⭐ on GitHub!
Acknowledgements
Strix builds on the incredible work of open-source projects like LiteLLM, Caido, Nuclei, Playwright, and Bubble Tea. Huge thanks to their maintainers!
Authorized use only. Strix actively tests the targets you point it at, so only run it against systems you own or have explicit, written permission to test, and stay within the agreed scope. Unauthorized testing is illegal in most jurisdictions. You alone are responsible for obtaining authorization and complying with the law. Strix is provided "as is" with no warranty or liability for misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Exposes FEDLIN's public security scanners as agent-callable tools over Streamable HTTP.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.
AI pentesting: run scans, triage vulnerabilities, review PRs, manage schedules and assets.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to execute Kali Linux security tools like nmap, sqlmap, and hydra in a secure, sandboxed environment. Provides both MCP and HTTP API interfaces for penetration testing and security assessment tasks.-
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to execute penetration testing commands and security tools on Kali Linux remotely. Supports automated reconnaissance, vulnerability scanning, and CTF solving through integration with 25+ offensive security tools like nmap, gobuster, and nuclei.16-
- AlicenseAqualityDmaintenanceEnables AI assistants to perform authorized penetration testing and security assessments by exposing 20+ Kali Linux security tools (nmap, sqlmap, gobuster, hydra, etc.) through a safe, validated interface with command allowlists, rate limiting, and input sanitization.191MIT
- AlicenseNot gradedqualityCmaintenanceEnables authorized security testing by letting LLM clients run Kali Linux tools inside an isolated Docker container.MIT