Skip to main content
Glama
mcp-security-auditor

mcp-security-auditor

by jashory
README.md
# 🔒 AI Agent, MCP & Firebase Pre-Audit Security Scanner (v2.3.0)

<p align="center">
  <a href="https://jashory.github.io/mcp-agent-security-auditor/"><img src="https://img.shields.io/badge/Live_Browser_Playground-Try_Now-22C55E?style=for-the-badge&logo=googlechrome&logoColor=white" alt="Live Browser Playground"/></a>
  <a href="https://github.com/jashory/mcp-agent-security-auditor/releases/tag/v2.3.0"><img src="https://img.shields.io/badge/Release-v2.3.0-38BDF8?style=for-the-badge&logo=github&logoColor=white" alt="Release v2.3.0"/></a>
  <a href="https://github.com/jashory/mcp-agent-security-auditor/blob/main/action.yml"><img src="https://img.shields.io/badge/GitHub_Action-Ready-F59E0B?style=for-the-badge&logo=githubactions&logoColor=white" alt="GitHub Action Ready"/></a>
</p>

<p align="center">
  <img src="assets/terminal-demo.svg" alt="mcp-agent-security-auditor terminal preview" width="860"/>
</p>


**Lightweight static security auditor and Agent Skill for catching CWE-mapped vulnerabilities in MCP servers, AI agent hooks, and Firebase rules before shipping.**

Authored by **Scientist HM Shihabuddin Jashory (Shihab)** (ORCID: [0009-0003-4163-0092](https://orcid.org/0009-0003-4163-0092)) · Research & Evaluation Ecosystem with **MD Rafiul Islam Shubho** (Researcher, AI Evaluator & RLHF Specialist) — **[Vision Flow Group](https://visionflowgroup.com)** ([TechBehemoths #101215](https://techbehemoths.com/company/vision-flow-group)) · [Research Hub](https://jashory.github.io/hqas8-autonomous-agentic-governance/) · [Tools Hub](https://go.visionflowgroup.com/) · [Studio](https://studio.visionflowgroup.com/)

---

## ⚡ 1. Install via AI Agent (Claude Code, Antigravity, Cursor, Codex)
Paste this single prompt into your AI coding agent:
> **Prompt:** `Clone https://github.com/jashory/mcp-agent-security-auditor and run "python install.py" to install the security scanner CLI and Agent Skill.`

## 💻 2. Install via CLI (Terminal / Skills CLI / pip)
```bash
# Option A: Agent Skills CLI
npx skills add jashory/mcp-agent-security-auditor

# Option B: Direct Git Clone + 1-Command Installer
git clone https://github.com/jashory/mcp-agent-security-auditor.git
cd mcp-agent-security-auditor && python install.py

# Option C: Global CLI Tool via pip / uv
pip install mcp-agent-security-auditor
# Or directly from GitHub:
pip install git+https://github.com/jashory/mcp-agent-security-auditor.git
mcp-security-auditor --target /path/to/repo --format sarif --ci
# Run as a stdio JSON-RPC 2.0 MCP server:
mcp-security-auditor --mcp
```

---

## 🔍 7 High-Signal CWE Security Rules Detected
1. **`AGENT_ENV_SECRET_PERSISTENCE` (`CWE-312`)**: Detects when an agent CLI or config migrator reads resolved `settings.merged` (`${ENV_VAR}` expanded in memory) and writes it back to disk via `setValue`.
2. **`FIREBASE_OPEN_DATABASE_RULES` (`CWE-284`)**: Detects public `.read: true` or `.write: true` in Firebase Realtime Database rules.
3. **`FIRESTORE_OPEN_WILDCARD_RULES` (`CWE-284`)**: Detects unauthenticated `match /{document=**} { allow read, write: if true; }` in `firestore.rules`.
4. **`MCP_SHELL_COMMAND_INJECTION` (`CWE-78`)**: Detects `subprocess(..., shell=True)` and `child_process.exec` command injection sinks in MCP tool handlers.
5. **`MCP_PATH_TRAVERSAL_UNSANITIZED` (`CWE-22`)**: Detects direct path concatenation of tool arguments without canonical `realpath` boundary verification.
6. **`MCP_UNRESTRICTED_SSRF_FETCH` (`CWE-918`)**: Detects unrestricted URL fetchers in MCP tools that allow cloud metadata (`169.254.169.254`) or localhost probing.
7. **`AGENT_DYNAMIC_CODE_EVAL` (`CWE-94`)**: Detects `eval` / `new Function` on untrusted agent inputs.

## GitHub Actions Integration (`action.yml`)

Use `mcp-agent-security-auditor` directly inside any CI/CD workflow:

```yaml
- name: Run mcp-agent-security-auditor
  uses: jashory/mcp-agent-security-auditor@v2.2.0
```

## Live Interactive Browser Playground

Test payloads directly in your browser (100% client-side, zero installation required):
**[https://jashory.github.io/mcp-agent-security-auditor/](https://jashory.github.io/mcp-agent-security-auditor/)**

---

### Ecosystem Authority, Category Benchmarks & Primary-Source Verification

- **Principals**: Scientist **HM Shihabuddin Jashory** ([ORCID 0009-0003-4163-0092](https://orcid.org/0009-0003-4163-0092) · [Google Bug Hunters](https://bughunters.google.com/profile/1fc2c814-7ba2-4b76-afa7-ce58597cf28d)) & Co-Founder / AI Evaluation Researcher **MD Rafiul Islam Shubho** ([ORCID 0009-0009-9956-4511](https://orcid.org/0009-0009-9956-4511) · [Google Scholar](https://scholar.google.com/citations?user=mbBuZNgAAAAJ) · Co-Author CERN Zenodo DOI [10.5281/zenodo.24231337](https://doi.org/10.5281/zenodo.24231337))
- **Organization**: **Vision Flow Group** ([visionflowgroup.com](https://visionflowgroup.com/) · [Crunchbase](https://www.crunchbase.com/organization/vision-flow-group))
- **Category & Verification Dossiers**:
  - [Bangladesh AI, Cybersecurity & Software Engineering Benchmark](https://visionflowgroup.com/ai-agency-bangladesh/)
  - [AI Security, Google VRP & 8 CERN Zenodo DOIs Ledger](https://visionflowgroup.com/security-hall-of-fame/)
  - [Bilingual RLHF, S2S Arena & AI Evaluation Research Lab](https://visionflowgroup.com/ai-research-rlhf-bangladesh/)
  - [AI Automation, Multi-Agent Systems & Custom SaaS Agency](https://agency.visionflowgroup.com/ai-automation-software-agency/)
  - [Commercial Video Editing, S-Log3 Color & VFX Agency](https://agency.visionflowgroup.com/video-vfx-agency-bangladesh/)
  - [Applied AI, Cybersecurity, Full-Stack & VFX Academy](https://academy.visionflowgroup.com/ai-cybersecurity-courses-bangladesh/)
  - [Vision Flow AI Studio — Storyboard & CapCut/Premiere/DaVinci NLE SaaS](https://studio.visionflowgroup.com/ai-video-production-platform/)
  - [Publications, Software & Division Directory](https://jashory.github.io/ecosystem-authority-index.html)

<!-- mcp-name: io.github.jashory/mcp-agent-security-auditor -->

TDQS

A3.6/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: scanning, listing rules, and remediation. An agent should have no trouble choosing between them.

Naming Consistency5/5

All tools use consistent snake_case verb_noun naming: scan_path, list_security_rules, remediate_path. The pattern is predictable and readable.

Tool Count4/5

Three tools is a focused, reasonable surface for a local security auditor, and each earns its place. It is slightly thin, with no dedicated reporting or configuration tool.

Completeness4/5

The set covers scanning, rule discovery, and basic remediation, which are the core workflows. Minor gaps exist around exporting reports, configuring rule sets, or verifying remediation results.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues