Skip to main content
Glama
mcp-security-auditor

mcp-security-auditor

by jashory

🔒 AI Agent, MCP & Firebase Pre-Audit Security Scanner (v2.3.0)

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) · Research & Evaluation Ecosystem with MD Rafiul Islam Shubho (Researcher, AI Evaluator & RLHF Specialist) — Vision Flow Group (TechBehemoths #101215) · Research Hub · Tools Hub · Studio


⚡ 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.

Related MCP server: MCP Shield

💻 2. Install via CLI (Terminal / Skills CLI / pip)

# 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:

- 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/


Ecosystem Authority, Category Benchmarks & Primary-Source Verification

Available Tools

3 tools
list_security_rulesA

List all 13 CWE-mapped static security rules implemented by mcp-agent-security-auditor.

Inputs: no named parameters.

remediate_pathB

Automatically redact hardcoded secrets or restore clean static redirect index.html in a local directory or file before git push.

Inputs: target (required).

scan_pathB

Run static Python AST, MCP schema, prompt-injection, and Firebase rules security scan on a local directory or file (secrets redacted by default).

Inputs: target (required), format.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    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

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Agent-native "safe to ship?" security gate for AI-generated code. Uses real parsers and inter-rocedural taint analysis (JS/TS, Python, Go) to flag the classes AI coding agents get wrong — secrets, SQL injection, SS, SSRF, path traversal, command injection, weak JWT/CORS — and ranks findings by confidence. Exposes a scan tool over MCP.
      1
      8 npm
      2
      MIT
    • A
      license
      C
      quality
      D
      maintenance
      Security scanner and MCP server that catches dangerous patterns in MCP servers and AI agent projects, such as leaked secrets, shell execution, and prompt-injection text. Runs as both a CLI and MCP server with CI-friendly severity gates.
      2
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables MCP-compatible AI agents to scan code for leaked secrets, copyleft licenses, unprotected routes, missing privacy policies, and risky card handling before committing or shipping.
      MIT