agent-bom 0.88.4

Open security scanner and self-hosted control plane for AI/MCP infrastructure.

agent-bom

Open security scanner and self-hosted control plane for AI/MCP infrastructure.

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

better-sqlite3@9.0.0  (npm package)
  |── OSV/GHSA finding  (critical · advisory-backed)
  |── sqlite-mcp  (MCP Server · unverified · root)
       |── Cursor IDE  (Agent · 4 servers · 12 tools)
       |── ANTHROPIC_KEY, DB_URL, AWS_SECRET  (Credential env names visible)
       |── query_db, read_file, write_file, run_shell  (Reachable tools)

 Fix: upgrade better-sqlite3 → 11.7.0

Blast radius is the core idea: package -> vulnerability finding -> MCP server (tools + credential env names) -> connected agents. This schematic explains the model; emitted findings are backed by the configured advisory sources.

Scan local agent configs, MCP servers, instruction files, lockfiles, containers, cloud posture, GPU surfaces, and runtime evidence.

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.

If you want an inspectable sample before scanning your own repo:

agent-bom samples first-run
agent-bom agents --inventory agent-bom-first-run/inventory.json -p agent-bom-first-run --enrich

The bundled first-run stack includes agent inventory, MCP server definitions, placeholder credential environment variable names, Python/npm manifests, and a prompt file. See docs/FIRST_RUN.md in the repository for the guided flow.

See the terminal demo

Recommended starting points

pip install agent-bom

agent-bom agents -p .                            # Repo + MCP + package blast radius
agent-bom samples first-run                      # Inspectable sample AI stack
agent-bom check flask@2.2.0 --ecosystem pypi     # Pre-install package verdict
agent-bom image nginx:latest                     # Container image scan
agent-bom agents -p . --remediate remediation.md # Fix-first remediation plan
pip install 'agent-bom[ui]'                      # once, if you want the dashboard
agent-bom serve                                  # API + dashboard + graph explorer

The base wheel is the scanner/CLI path. Install optional surfaces explicitly: pip install 'agent-bom[mcp-server]' for MCP server mode and pip install 'agent-bom[ui]' for the local API/dashboard process. If an extra is missing, the command exits with the matching install hint.

Self-hosted pilot:

curl -fsSL https://raw.githubusercontent.com/msaad00/agent-bom/main/deploy/docker-compose.pilot.yml -o docker-compose.pilot.yml
docker compose -f docker-compose.pilot.yml up -d
# Dashboard -> http://localhost:3000

Production chart from a checked-out repo:

helm upgrade --install agent-bom deploy/helm/agent-bom \
  --namespace agent-bom --create-namespace \
  -f deploy/helm/agent-bom/examples/eks-production-values.yaml

Product views

Dashboard

Agent mesh graph

What it scans

• Agents + MCP — MCP clients, servers, tools, transports, trust posture
• Skills + instructions — CLAUDE.md, AGENTS.md, .cursorrules, .windsurfrules, skills/*
• Package risk — software supply chain scanning with enrichment and blast radius
• Container images + IaC — native OCI parsing plus Dockerfile, Terraform, CloudFormation, Helm, and Kubernetes coverage
• Cloud AI — cloud and AI infrastructure posture across major supported providers
• Secrets + runtime — MCP proxy, Shield SDK, secrets, and redaction surfaces
• Compliance + evidence — mapped governance plus ZIP evidence bundles for auditors

Key features

• Blast radius mapping — package → vulnerability finding → MCP server (tools + credential env names) → connected agents
• CWE-aware impact — RCE shows credential exposure, DoS does not
• Portable outputs — SARIF, CycloneDX, SPDX, HTML, graph, JSON, ZIP evidence bundles, and more
• MCP server mode — expose agent-bom capabilities directly to MCP clients like Claude, Cursor, Windsurf, and Cortex CoCo / Cortex Code
• Skill bundle identity — stable bundle hashes for skill and instruction file review
• Dependency confusion detection — flags internal naming patterns
• VEX generation — auto-triage with CWE-aware reachability

Read-only. Agentless. No secrets leave your machine unless you explicitly enable an outbound integration.

How the data moves

Blast radius

Links

• GitHub
• Docker Hub
• Documentation
• Product brief
• Verified metrics
• Enterprise controls map
• Discord