Adds governance and compliance enforcement to AI coding workflows by exposing Sentrik's scanning engine through MCP. The server gives Claude and other agents real-time access to compliance rules (OWASP, SOC 2, HIPAA, PCI-DSS), scan results, and remediation guidance so they can write compliant code from the start rather than catching violations in PR review. Useful if you're generating code at speed with AI agents and need to enforce security policies, regulatory standards, or architectural rules before commits ship. The underlying CLI supports 158+ rules across 5 free standards packs, with paid tiers adding medical device (FDA IEC 62304), government (NIST, CMMC), and automotive standards.
Governance runtime for AI-generated code
Scan, gate, and trace compliance automatically — before it ships.
Website • Docs • Community • Pricing
Sentrik is a CLI + dashboard that enforces coding standards, compliance rules, and security policies on every commit. Built for teams using AI coding agents (Claude Code, Cursor, Copilot) where code is generated faster than humans can review it.
The problem: AI agents write code that works but may violate security policies, compliance requirements, or architectural standards. Nobody catches it until audit time.
The solution: Sentrik scans every change against regulatory standards (OWASP, SOC 2, HIPAA, PCI-DSS, FDA IEC 62304, and more), gates PRs that fail, and generates audit-ready evidence.
pip install sentrik
Installing gives you the free tier immediately — 6 standards packs, 193 rules, no license key or sign-up. Paid tiers are activated with a license key from hello@sentrik.dev.
# 1. Initialize your project (auto-detects language, frameworks, CI)
sentrik init
# 2. Scan your code
sentrik scan
# 3. Enforce the gate in CI (exit 1 on failure)
sentrik gate
# 4. Launch the dashboard
sentrik dashboard
Sentrik includes 6 standards packs with 193 rules for free:
| Pack | Rules | What it catches |
|---|---|---|
| OWASP Top 10 | 69 | SQL injection, XSS, auth flaws, SSRF, and more |
| SOC 2 | 30 | Trust services criteria for security & availability |
| Python Security | 18 | eval/exec, pickle, subprocess, Django/Flask vulns |
| Go Security | 15 | Injection, crypto misuse, unsafe, concurrency bugs |
| Supply Chain Security | 26 | SLSA, SBOM, dependency integrity, AI tool supply chain |
| C/C++ Coding Standards | 35 | Modern C/C++ safety and security practices |
Plus built-in commands at every tier:
sentrik scan / sentrik gate - Scan and enforcesentrik vulns - Dependency vulnerability scanning (CVEs)sentrik sbom - Software bill of materialssentrik secrets - Hardcoded secrets detectionsentrik dashboard - Web UI with findings, charts, and reportssentrik threat-model - STRIDE threat analysissentrik quality-score - Code quality scoring (0-100)| Free | Team | Organization | |
|---|---|---|---|
| Standards packs | 6 (193 rules) | 18 (475 rules) | 24 (595 rules) |
| OWASP, SOC 2, Supply Chain, C/C++ | Yes | Yes | Yes |
| HIPAA, PCI-DSS, ISO 27001, GDPR | - | Yes | Yes |
| FDA IEC 62304, NIST, CMMC, Cloud IaC | - | Yes | Yes |
| MISRA-C, DO-178C, ISO 26262 | - | - | Yes |
| Vulnerability scanning | Yes | Yes | Yes |
| Dashboard | Yes | Yes | Yes |
| Work item reconciliation | - | Yes | Yes |
| Custom rule packs | 5 | 25 | 100 |
| Parallel scanning | - | - | Yes |
| Governance & audit log | - | - | Yes |
Paid tiers are available by contacting hello@sentrik.dev — see sentrik.dev/pricing.
# .github/workflows/sentrik.yml
name: Sentrik Gate
on: [pull_request]
jobs:
gate:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: maxgerhardson/sentrik-community@v1
That's it — one line. The action auto-detects PR context, runs the gate, uploads SARIF to GitHub Code Scanning, and attaches the findings report as an artifact.
With options:
- uses: maxgerhardson/sentrik-community@v1
with:
packs: "owasp-top-10,soc2,supply-chain-security"
fail-on: "critical,high"
license-key: ${{ secrets.SENTRIK_LICENSE_KEY }}
Using outputs:
- uses: maxgerhardson/sentrik-community@v1
id: sentrik
- run: echo "Found ${{ steps.sentrik.outputs.findings-count }} findings"
if: always()
sentrik:
image: maxgerhardson/sentrik:latest
script:
- sentrik gate --git-range "origin/main...HEAD"
rules:
- if: $CI_PIPELINE_SOURCE == "merge_request_event"
- script: |
pip install sentrik
sentrik gate --git-range "origin/main...HEAD"
displayName: Sentrik Gate
Sentrik works as an MCP server for AI coding agents:
# Start MCP server for Claude Code, Cursor, VS Code
sentrik mcp-server
The MCP server gives AI agents real-time access to compliance rules, scan results, and remediation guidance — so they write compliant code from the start.
# .sentrik/config.yaml
standards_packs:
- owasp-top-10
- supply-chain-security
gate:
fail_on:
- critical
- high
standards_packs:
- owasp-top-10
- hipaa
- fda-iec-62304
- supply-chain-security
gate:
fail_on:
- critical
- high
- medium
standards_packs:
- owasp-top-10
- pci-dss
- soc2
- supply-chain-security
gate:
fail_on:
- critical
- high
standards_packs:
- owasp-top-10
- nist-800-53
- cmmc
- supply-chain-security
gate:
fail_on:
- critical
- high
- medium
| Channel | For |
|---|---|
| GitHub Discussions | Questions, ideas, community help |
| support@sentrik.dev | Direct support (paid tiers) |
| sales@sentrik.dev | Pricing and licensing |
Proprietary. Free tier available forever with no credit card required.
GUARD_LICENSE_KEYsecretSentrik license key for Team/Organization features (optional — free tier works without it)
com.exploit-intel/eip-mcp
dmontgomery40/pentest-mcp
pantheon-security/notebooklm-mcp-secure
cyanheads/pentest-mcp-server
io.github.akhilucky/ai-firewall-mcp