Open security scanner for AI supply chain — agents, MCP servers, packages, containers, cloud, GPU, and runtime.

Start with the demo, then choose the entrypoint that matches your first job: repo scan, image scan, cloud posture, fix plan, dashboard, or runtime review.

CVE-2025-1234  (CRITICAL · CVSS 9.8 · CISA KEV)
  |── [email protected]  (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

Blast radius is the core idea: CVE -> package -> MCP server -> agent -> credentials -> tools.

agent-bom scans local agent configs, MCP servers, instruction files, lockfiles, containers, cloud posture, GPU surfaces, and runtime evidence. CWE-aware impact keeps a DoS from being reported like credential compromise.

Try the built-in demo first:

agent-bom agents --demo --offline

The demo uses a curated sample so the output stays reproducible across releases. For real scans, run agent-bom agents, or add -p . to fold project manifests and lockfiles into the same result.

Choose the view that matches what you need:

• CLI: fast local proof that blast radius and remediation are real
• Graph: one focused path first, then expand only when needed
• Dashboard: persistent state, diff, and review

Pick the entrypoint that matches your first job:

pip install agent-bom                  # Standard CLI install
# pipx install agent-bom               # Isolated global install
# uvx agent-bom --help                 # Ephemeral run without installing

agent-bom agents                              # Discover + scan local AI agents and MCP servers
agent-bom agents -p .                         # Scan project lockfiles/manifests plus agent/MCP context
agent-bom where                               # Show MCP discovery paths checked on this machine
agent-bom mesh --project .                    # Show the live agent / MCP topology
agent-bom skills scan .                       # Scan CLAUDE.md, AGENTS.md, .cursorrules, skills/*
agent-bom check [email protected] --ecosystem pypi  # Pre-install CVE gate
agent-bom image nginx:latest                  # Container image scan
agent-bom iac Dockerfile k8s/ infra/main.tf   # IaC scan across one or more paths

agent-bom agents -p . --remediate remediation.md                    # Fix-first plan with versions and reachable impact
agent-bom agents -p . --compliance-export fedramp -o evidence.zip   # ZIP evidence bundle for auditors
pip install 'agent-bom[ui]'                                         # once, for API + dashboard
agent-bom serve                                                     # Review the same findings in the dashboard and graph

agent-bom cloud aws                     # Cloud AI posture + CIS benchmarks
agent-bom agents -f cyclonedx -o bom.json  # AI BOM / SBOM export
agent-bom check [email protected] -e pypi -f json  # Machine-readable pre-install verdict
agent-bom report diff before.json after.json -f json  # CI-friendly diff output
agent-bom agents -p . --compliance-export fedramp -o fedramp-evidence.zip  # Auditor-ready evidence bundle
agent-bom graph report.json                # Blast radius graph / graph HTML inputs
agent-bom proxy "npx @mcp/server-fs /ws"   # MCP security proxy
agent-bom secrets src/                  # Hardcoded secrets + PII
agent-bom verify agent-bom              # Verify this installation
agent-bom verify [email protected]        # Package integrity verification
agent-bom verify --model-dir ./models   # Model weight hash verification
agent-bom serve                         # API + Next.js dashboard

• Blast radius that maps CVE -> package -> MCP server -> agent -> credentials -> tools
• One operator path across CLI, CI, API, dashboard, remediation, and MCP tools
• AI-native coverage across agents, MCP, runtime, containers, cloud, IaC, and GPU surfaces
• Compliance evidence bundles for cmmc, fedramp, and nist-ai-rmf

These screenshots come from the live product path, using the built-in demo data pushed into the API.

Risk summary, posture, and the highest-value attack paths without waiting on deep scan hydration.

The graph starts scoped to one agent and the vulnerable path in view, then expands only when the operator asks for more.

Reach, severity, fix version, and framework context stay in one review table so the operator can act without jumping between pages.

Default scans use the bundled MITRE ATT&CK + CAPEC catalog, so results stay deterministic and offline-friendly. Refresh to a newer upstream snapshot only when you want to:

agent-bom db update-frameworks
agent-bom db status

The active catalog metadata is also surfaced in JSON output (framework_catalogs) and the API at /v1/frameworks/catalogs. Long-lived connected deployments can point at a synced catalog or opt into runtime refresh with AGENT_BOM_MITRE_CATALOG_MODE.

One path: discover, analyze, persist, then operate across CLI, CI, API, dashboard, and exports.

Blast radius stays explicit in the data model instead of being hand-waved as a generic finding list.

pip install agent-bom                        # CLI
docker run --rm agentbom/agent-bom agents    # Docker

Product references:

• docs/PRODUCT_BRIEF.md
• docs/PRODUCT_METRICS.md
• docs/ENTERPRISE.md

Use the GitHub Action when you want a fast CI gate: one step, one gate, SARIF in the Security tab, and a clean exit code for CI.

Repo + MCP + instruction files

- uses: msaad00/[email protected]
  with:
    scan-type: scan
    severity-threshold: high
    upload-sarif: true
    enrich: true
    fail-on-kev: true

Container image gate

- uses: msaad00/[email protected]
  with:
    scan-type: image
    scan-ref: ghcr.io/acme/agent-runtime:sha-abcdef
    severity-threshold: critical

IaC gate

- uses: msaad00/[email protected]
  with:
    scan-type: iac
    iac: Dockerfile,k8s/,infra/main.tf
    severity-threshold: high

Air-gapped / pre-synced CI

- uses: msaad00/[email protected]
  with:
    auto-update-db: false
    enrich: false

• Developer endpoints: run agent-bom agents locally or via MDM for workstation inventory and posture.
• CI/CD: use the GitHub Action for PR gates, SARIF upload, image gates, and IaC checks.
• Central security team: deploy agent-bom serve for fleet ingestion, posture, and audit exports.
• Air-gapped / isolated: run the Docker image with --offline and auto-update-db: false using a pre-synced local DB.

See docs/ENTERPRISE_DEPLOYMENT.md for rollout patterns, auth models, and storage backends.

36 security tools available inside any MCP-compatible AI assistant:

{
  "mcpServers": {
    "agent-bom": {
      "command": "uvx",
      "args": ["agent-bom", "mcp", "server"]
    }
  }
}

Also on Glama, Smithery, MCP Registry, and OpenClaw.

git clone https://github.com/msaad00/agent-bom.git && cd agent-bom
pip install -e ".[dev-all]"
pytest && ruff check src/

See CONTRIBUTING.md | docs/CLI_DEBUG_GUIDE.md | SECURITY.md | CODE_OF_CONDUCT.md

Apache 2.0 — LICENSE