security MCP Server
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
Discovered via github-seeds:mcp-hot and last synced 3mo ago.
1. Install the package
npx -y agent-security-scanner-mcp
2. Add to claude_desktop_config.json
{
"mcpServers": {
"agent-security-scanner-mcp": {
"command": "npx",
"args": [
"agent-security-scanner-mcp"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
Data exfiltration/exposure below threshold
`sbom_check_hallucinations`
85-100
Controls
Sensitive data exposure below threshold
Destructive ops (rm -rf), RCE (curl\
Scan only changed files in git diff
Data exfiltration below threshold
Action
Base64 encoded commands, ROT13, fragmented instructions
Auto-fix all detected vulnerabilities (120 fix templates)
Check plugin health: engine status, daemon status, package data availability
Description
Verify a package name isn't AI-hallucinated (4.3M+ packages)
Pre-execution safety check for agent actions (bash, file ops, HTTP). Returns ALLOW/WARN/BLOCK
Generate HTML or JSON audit report from SBOM with vulnerability data
Compare current SBOM against baseline, detect added/removed/changed packages
Supply chain, code security, crypto, auth, drift
Cryptographic controls adequate
No critical third-party vulnerabilities
Path value is present and non-null
Verify all SBOM packages exist in official registries
Data privacy, encryption, third-party risks
Authentication/authorization adequate
No hallucinated packages
Exact equality
Deleting sensitive or system paths
string
string
0 critical/error issues
SQL injection, command injection, deserialization, SSRF, path traversal
Scan entire project with A-F security grading
List available security rules and fix templates
✅ `ANTHROPIC_API_KEY`
No critical code security findings
Encryption/transport adequate
`sbom_diff`
string
string
object
Examples
Writing to sensitive paths (/etc, /root, ~/.ssh)
boolean
CGEventTapCreate, pynput, SetWindowsHookEx, NSEvent.addGlobalMonitor
array
Deep security scan of an OpenClaw skill: prompt injection, AST+taint code analysis, ClawHavoc malware signatures, supply chain, rug pull. Returns A-F grade
Dependency drift tracked
Tools Used
Less than or equal
65-84
string
1-2 error issues, no critical
SQL injection, XXE, LDAP injection, insecure deserialization, CSRF
`npx agent-security-scanner-mcp init cursor`
Type
Value
Why
Generate CycloneDX v1.5 SBOM for a project (8 lock file formats, 7 manifest formats)
API Key Required
No hallucinated packages
string
0-19
boolean
array
11+ error issues or any critical
## Hallucination Detection Ecosystems
`npx agent-security-scanner-mcp init opencode`
string
Evaluate project against compliance frameworks with evidence collection
—
Software dependency inventory exists
What It Checks
`sbom_generate`
Greater than or equal
40-64
string
string
3-5 error issues
SQL injection, command injection, path traversal, race conditions
`npx agent-security-scanner-mcp init windsurf`
array
Tokens
Build Tool
No critical dependency vulnerabilities
`sbom_scan_vulnerabilities`
Fix Strategy
20-39
string
What It Checks
string
6-10 error issues
SQL injection, XSS, command injection, deserialization, file inclusion
`npx agent-security-scanner-mcp init cline`
array
Aggregate results, avoid context overflow
AI agent security, prompt injection, hallucination
Third-party dependency inventory
string
string
Reading sensitive paths (private keys, credentials, /etc/passwd)
SQL injection, XSS, command injection, prototype pollution, insecure crypto
~3.3M
`npx agent-security-scanner-mcp init`
Requests to private IP ranges, suspicious exfiltration endpoints
string
Criteria
Same as JavaScript + type-specific patterns
~554K
Description
What Happens
Vulnerabilities Detected
Detection Method
`npx agent-security-scanner-mcp init cody`
boolean
Need complete audit trail
> **Two package variants:** The base package (`agent-security-scanner-mcp`, 2.7 MB) includes 6 ecosystems. npm hallucination detection requires the full package (`agent-security-scanner-mcp-full`, 10.3 MB) because the npm registry bloom filter is 7.6 MB. --- ## Installation ### Install ```bash npm install -g agent-security-scanner-mcp ``` Or use directly with `npx` — no install required: ```bash npx agent-security-scanner-mcp ``` ### Prerequisites - **Node.js >= 18.0.0** (required) - **Python 3.x** (required for analyzer engine) - **PyYAML** (`pip install pyyaml`) — required for rule loading - **tree-sitter** (optional, for enhanced AST detection): `pip install tree-sitter tree-sitter-python tree-sitter-javascript` ### Client Setup
Path
Behavior
### Example Usage ```json // Minimal - just counts (~50 tokens) { "file_path": "app.py", "verbosity": "minimal" } // Returns: { "total": 5, "critical": 2, "warning": 3, "message": "Found 5 issue(s)" } // Compact - actionable info (~200 tokens, default) { "file_path": "app.py", "verbosity": "compact" } // Returns: { "issues": [{ "line": 42, "ruleId": "...", "severity": "error", "fix": "..." }] } // Full - complete metadata (~2,500 tokens) { "file_path": "app.py", "verbosity": "full" } // Returns: { "issues": [{ ...all fields including CWE, OWASP, references }] } ``` ### Recommended Verbosity by Scenario
minimal
✅ `OPENAI_API_KEY`
Type
Bulk-check all imports in a file for hallucinated packages
Cross-reference SBOM against OSV.dev for CVEs with severity filtering
Need line numbers and fix suggestions
98% reduction
Scan MCP server source for vulnerabilities: unicode poisoning, name spoofing, rug pull detection, manifest analysis. Returns A-F grade
📖 Full documentation: [`code-review-agent/README.md`](./code-review-agent/README.md) --- ## 📦 SBOM / Supply Chain Analysis (New in v4.1.0) Generate Software Bill of Materials (SBOM) and analyze dependencies for vulnerabilities across your entire supply chain. ### Quick Start ```bash # Generate SBOM for current project npx agent-security-scanner-mcp sbom-generate . # Scan for vulnerabilities against OSV.dev npx agent-security-scanner-mcp sbom-vulnerabilities . # Check for hallucinated packages npx agent-security-scanner-mcp sbom-check-hallucinations . # Compare against baseline (CI/CD) npx agent-security-scanner-mcp sbom-diff . --save-baseline # First run npx agent-security-scanner-mcp sbom-diff . # Subsequent runs # Generate HTML audit report npx agent-security-scanner-mcp sbom-report . --format html ``` ### Supported Ecosystems
Send code to webhook, read .env files, push to external repo
Look up compliance controls with evaluation criteria (AIUC-1, SOC2, GDPR)
CLI Fallback
MultiEdit", "command": "npx agent-security-scanner-mcp scan-security \"$TOOL_INPUT_file_path\" --verbosity minimal" } ] } } ``` ### Hook Behavior - **Non-blocking:** Hooks report findings but don't prevent file writes - **Minimal output:** Uses `--verbosity minimal` to avoid context overflow - **Automatic:** Runs on every file modification without manual intervention --- ## OpenClaw Integration [OpenClaw](https://openclaw.ai) is an autonomous AI assistant with broad system access. This scanner provides security guardrails for OpenClaw users. ### Install ```bash npx agent-security-scanner-mcp init openclaw ``` This installs a skill to `~/.openclaw/workspace/skills/security-scanner/`. ### OpenClaw-Specific Threats The scanner includes 30+ rules targeting OpenClaw's unique attack surface:
真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。
Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators
Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS
Implements eBPF-based security monitoring using Cilium Tetragon for real-time process execution tracking, network connection observability, file access auditing, and runtime enforcement. Covers TracingPolicy CRD authoring with kprobe/tracepoint hooks, in-kernel filtering via matchArgs/matchBinaries selectors, JSON event export, and integration with SIEM pipelines. Use when building kernel-level runtime security observability for Linux hosts or Kubernetes clusters.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Learn how to use the absolute-audit Claude skill. Complete guide with installation instructions and examples.
Learn how to use the token-scam-analysis Claude skill. Complete guide with installation instructions and examples.
Learn how to use the absolute-upgrade Claude skill. Complete guide with installation instructions and examples.