README.md
AI supply chain security scanner for MCP servers and AI agents.
Your AI agent's dependencies have a CVE. Which credentials leak?
CVE-2025-1234 (CRITICAL · CVSS 9.8 · CISA KEV)
|── better-sqlite3@9.0.0 (npm)
|── sqlite-mcp (MCP Server · unverified · root)
|── Cursor IDE (Agent · 4 servers · 12 tools)
|── ANTHROPIC_KEY, DB_URL, AWS_SECRET (Credentials exposed)
|── query_db, read_file, write_file, run_shell (Tools at risk)
Fix: upgrade better-sqlite3 → 11.7.0
agent-bom maps the blast radius: CVE → package → MCP server → AI agent → credentials → tools.
pip install agent-bom
agent-bom agents
What it does
Security scanner purpose-built for AI infrastructure and supply chain.
AI Supply Chain Security:
- Discovers AI agents + MCP servers — 30 client types, auto-detected from config files
- Scans source code — AST analysis extracts system prompts, guardrails, tool signatures from Python AI frameworks (LangChain, CrewAI, OpenAI Agents SDK, and 7 more)
- Generates an AI BOM — CycloneDX 1.6 with native ML extensions (modelCard, datasets, training metadata)
- Scans for CVEs — 15 ecosystems checked against OSV + NVD + GHSA + EPSS + CISA KEV
- Maps blast radius — CVE → package → MCP server → AI agent → credentials → tools
- Detects secrets — 34 credential patterns + 11 PII patterns across source, config, and .env files
- Enforces at runtime — MCP proxy with 112 detection patterns, PII redaction, zero-trust session isolation
- Verifies supply chain — SLSA provenance (npm), PEP 740 attestations (PyPI), Go checksum DB
Also scans: container images, filesystems, IaC (138 rules), cloud posture (AWS/Azure/GCP CIS benchmarks).
Shield SDK — drop-in Python middleware for any AI agent pipeline:
from agent_bom.shield import Shield
shield = Shield(deep=True)
alerts = shield.check_tool_call("exec", {"command": "rm -rf /"})
safe = shield.redact(response_text) # [REDACTED:OpenAI API Key]
Read-only. Agentless. No secrets leave your machine.
Quick start
pip install agent-bom
# AI agent discovery + vulnerability scanning + blast radius
agent-bom agents
# Pre-install CVE gate
agent-bom check flask@2.0.0
# MCP security proxy (112 patterns, 7 detectors, PII redaction)
agent-bom proxy "npx @mcp/server-filesystem /tmp"
# Container image scan
agent-bom image nginx:latest
# IaC misconfigurations (138 rules: Dockerfile, K8s, Terraform, CloudFormation, Helm)
agent-bom iac Dockerfile k8s/ infra/main.tf
# Cloud posture + CIS benchmarks
agent-bom cloud aws
# Dependency graph export (Neo4j, GraphML, Graphviz, Mermaid)
agent-bom graph report.json --format cypher --output import.cypher
# Red team — test your defenses (100% detection, 0% false positives)
python -c "from agent_bom.red_team import run_red_team; print(run_red_team()['detection_rate'])"
All commands
Scanning: agents, image, fs, iac, sbom, secre
Tools (3)
agent-bom-scanScans AI agents and MCP servers for vulnerabilities and security risks.agent-bom-proxyRuns an MCP security proxy with detection patterns and PII redaction.agent-bom-checkPerforms a CVE gate check on specific packages.Configuration
claude_desktop_config.json
{"mcpServers": {"agent-bom": {"command": "agent-bom", "args": ["proxy", "npx", "@mcp/server-filesystem", "/tmp"]}}}Try it
→Scan my current environment for AI agents and MCP servers to identify potential security vulnerabilities.
→Run the security proxy for my filesystem MCP server to enable PII redaction and threat detection.
→Check if the flask package version 2.0.0 has any known CVEs.
→Generate a security report for my current AI agent setup including blast radius mapping.