What it is

agent-bom discovers software, cloud, identity, AI-agent, and MCP evidence; turns it into findings and relationship graphs; and carries the same evidence into CI, a self-hosted control plane, and runtime policy enforcement.

  • Scan locally or in CI and export console, JSON, SARIF, SBOM, HTML, and graph artifacts.
  • Centralize findings, compliance evidence, jobs, inventory, and investigations in a control plane you run.
  • Enforce MCP and tool-call policy through the gateway, proxy, and Shield SDK surfaces.

The product uses one Finding + UnifiedGraph model across CLI, API, UI, and MCP. It does not require a hosted account for local scanning.

Quick start

Run against the repository in your current directory:

pip install agent-bom
agent-bom scan .

The console shows inventory, findings, and reachable impact. Save an artifact with agent-bom scan . -f sarif -o findings.sarif, or follow the first-run guide for exit codes, formats, and CI use.

Use the curated, explicitly synthetic sample when you only want to inspect the output shape:

agent-bom scan --demo --offline

The sample intentionally contains blocking findings, so exit status 1 is expected.

How it works

  1. Read-only collectors inventory the selected repository, image, agent configuration, or connected cloud scope.
  2. Deterministic scanners normalize evidence into findings, packages, assets, identities, and relationships.
  3. Exports, the control plane, and runtime policy consume that same evidence model.

The browser experience keeps the evidence shared while presenting task-focused workspaces: fix-first findings, path-first investigation, control evidence, and posture summaries. Graph views preserve provenance where source evidence provides it: collected, inferred, static, and runtime relationships remain distinct, while unavailable provenance is not upgraded to observed. Interactive views expose fit, zoom, pan, layout, and personal positioning controls.

Who it is for

Role Start here Primary outcome
Local developers agent-bom scan . Find and explain issues before code leaves the workstation
AppSec agent-bom scan . -f sarif -o findings.sarif Triage reachable findings and enforce CI gates
Security engineers pip install 'agent-bom[ui]' && agent-bom serve Investigate exposure paths, identities, and evidence provenance
Platform / SRE agent-bom connect aws Centralize estate inventory, jobs, and runtime controls
GRC / audit agent-bom report compliance-narrative scan.json Review control mappings and export evidence with explicit gaps
Leadership / CISO pip install 'agent-bom[ui]' && agent-bom serve Review posture, coverage, material risk, and change over time
AI / MCP owners pip install 'agent-bom[mcp-server]' && agent-bom mcp server Inventory tools and apply allow, warn, or block decisions

AppSec and GRC remain separate workflows: findings and reachability are not presented as audit certification. See product boundaries.

The gallery uses deterministic sample data, visibly labeled in the UI. It is product-state proof, not customer or advisory evidence.

Overview Findings
Investigation Remediation
Cloud and environment lineage Agent mesh

Capture protocol

Self-host

Start the loopback control plane:

pip install 'agent-bom[ui]'
agent-bom serve

For a shared deployment, use the documented Docker or Helm path and configure real identity, TLS, PostgreSQL, encryption, and audit keys before exposing it.

Target Start here
Docker Compose Pilot compose
Helm / Kubernetes helm install agent-bom oci://ghcr.io/msaad00/charts/agent-bom --version 0.99.0
EKS Terraform module
Air-gapped Image bundle guide

Pins target v0.99.0, the version this tree builds. Until that release is published, use the version shown on the PyPI badge above.

Deployment overview · Enterprise configuration · Cloud connections

Need First action Artifact or next step
GitHub CI uses: msaad00/[email protected] SARIF, PR summary, and a policy exit code
Cloud evidence agent-bom connect aws Stored connection reference; run scans from the control plane
Runtime gateway agent-bom gateway serve --from-control-plane http://127.0.0.1:8422 --bind 127.0.0.1:8090 Allow, warn, and block audit events
Agent interface agent-bom mcp server 77 MCP tools, 6 resources, and 8 workflow prompts
Agent distribution Smithery · Glama · MCP registry · Docker MCP Registry-specific installation metadata

The CLI, Docker, API, Helm chart, MCP server, gateway, and SDK are distribution surfaces of the same product. EKS remains a deployment profile; Snowflake and Snowpark remain connector/runtime integrations rather than hosted-core dependencies.

Surface Get it
Python package pip install agent-bom — PyPI
Container docker pull agentbom/agent-bom — Docker Hub
Kubernetes helm install agent-bom oci://ghcr.io/msaad00/charts/agent-bom
GitHub Action msaad00/agent-bom
MCP server pip install 'agent-bom[mcp-server]' && agent-bom mcp server
MCP registries Smithery · Glama · MCP registry · Docker MCP
SDKs Python · TypeScript · Go

Trust

  • Read-only discovery by default; runtime write decisions are separate and explicit.
  • Credentials are write-only where stored, encrypted at rest, and never returned by API responses.
  • API and control-plane routes are tenant scoped and auth protected outside explicit local mode.
  • Missing evidence is shown as unavailable or partial, never converted into a factual zero.
  • Public examples and screenshots use deterministic synthetic identifiers only.

Threat model · Release verification · Security policy · MCP security model

Contributing

Start with CONTRIBUTING.md, AGENTS.md, and the open issues.

Apache-2.0 licensed.