agent-bom
AI supply-chain BOM: supported agents, MCP servers and AI packages, and what each one can reach.
For AppSec teams and developers who run Claude Code, Cursor, Codex or any MCP client: see which agents, MCP servers, tools and packages are installed, which are vulnerable, and what each one can reach. Local scans need no account. Try it in your browser first, no install.
With uv installed, run from the repository you want to inspect:
uvx agent-bom scan . -f html -o agent-bom-report.html
Open agent-bom-report.html for inventory, findings and fix guidance. Run it
again later to see what changed. The scan stays inside this repository. No MCP
configuration? Package findings still apply. Incomplete evidence is not a clean
result: what a scan does and does not establish.
For a bundled sample, run uvx agent-bom scan --demo --offline; status 1 is
the expected security verdict for its blocking findings.
| Where | Start with | You get |
|---|---|---|
| On your laptop | uvx agent-bom scan . and claude mcp add agent-bom -- uvx agent-bom mcp server |
Findings with fixes, a delta on every rescan, agent-bom as a tool in your coding agent |
| In your team | uses: koda-ai-studio/agent-bom@v0 on pull requests plus a weekly schedule: |
A PR gate with a findings comment and SARIF, and a weekly rescan for new CVEs |
| Across your org | agent-bom up, then Docker Compose or the Helm chart |
Retained scans, one graph of agents, servers, packages and credentials, SSO and audit in your infrastructure |
Recommended starting points
pip install agent-bom
agent-bom scan . # Repo + MCP + package blast radius
agent-bom samples first-run # Inspectable sample AI stack
agent-bom scan --inventory agent-bom-first-run/inventory.json -p agent-bom-first-run --enrich
agent-bom check flask@2.2.0 --ecosystem pypi # Pre-install package verdict
agent-bom image nginx:latest # Container image scan
agent-bom scan . --remediate remediation.md # Fix-first remediation plan
agent-bom quickstart --dry-run --offline # Sample-data and API/UI next steps
pip install 'agent-bom[ui]' # once, if you want the dashboard
agent-bom serve --persist ~/.agent-bom/control-plane.db # restart-safe local control plane
The base wheel is the scanner/CLI and includes MCP server mode
(agent-bom mcp server). agent-bom[ui] adds the local API and dashboard;
agent-bom[all] adds the supported first-run extras (MLflow stays separate
until its upstream CVE backlog is fixed). A missing extra exits with the
matching install hint. The guided flow is docs/FIRST_RUN.md in the repository.
Self-hosted pilot:
curl -fsSL https://raw.githubusercontent.com/koda-ai-studio/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
For production, configure the database, identity and ingress settings in a release checkout. Follow the required secret bootstrap and wait for all four target Secrets before installing the workload:
helm upgrade --install agent-bom oci://ghcr.io/koda-ai-studio/charts/agent-bom --version 0.114.0 \
--namespace agent-bom --create-namespace \
-f deploy/helm/agent-bom/examples/eks-production-values.yaml
Product views
Follow Document Intake Agent → document-tools MCP → pillow@9.0.0 → CVE-2023-4863. Sample data; dashed links are modeled, not observed.
A repository pin, image SBOM and Kubernetes workload resolve to one package; the image inventory and deployment occurrence stay distinct. Sample data; a graph path does not prove execution or exploitation.
Explore the reference evidence lab · Graph guide
What it covers
- Agents + MCP — MCP clients, servers, tools, transports, trust posture
- Skills + instructions —
CLAUDE.md,AGENTS.md,.cursorrules,.windsurfrules,skills/*, with stable bundle hashes for review - Package risk — 15 package ecosystems (including
mix.lock/pubspec.lockfor Hex and Pub) with OSV/GHSA enrichment, dependency-confusion detection and blast radius - CWE-aware impact — RCE shows credential exposure, DoS does not; symbol-level CVE reachability when OSV/GHSA carry affected symbols (Python, npm, Go), with VEX generation
- AI models + datasets — malicious-model detection via safe pickle-opcode disassembly (no execution), model/dataset cards, and target-scoped PII/PHI dataset-file scanning
- Container images + IaC — native OCI parsing plus Dockerfile, Terraform, CloudFormation, Helm, and Kubernetes coverage
- Cloud estate — read-only, gated asset inventory across AWS/Azure/GCP plus AI/GPU posture and CIS benchmarks
- Identity (NHI) — non-human identity discovery (Okta/Entra), credential-expiry posture, and access-review campaigns
- LLM cost — spend forecasting, budget runway, chargeback/allocation, and seasonal-aware spend-anomaly detection
- Secrets + runtime — MCP proxy/gateway, inline firewall enforcement, A2A/MCP auth posture, Shield SDK, secrets, and redaction surfaces
- MCP server mode — start with 8 scan-profile tools; use
agent-bom mcp server --profile fullfor the complete catalog of 100 MCP tools, 7 resources, and 8 workflow prompts in Claude, Cursor, Windsurf, and Cortex CoCo / Cortex Code - Outputs + evidence — SARIF, CycloneDX, SPDX, OCSF, HTML, graph, JSON and ZIP evidence bundles for auditors
Discovery and static/cloud scanning are read-only by default. Explicit disk side-scans create temporary cloud resources and need additional permissions. Proxy, gateway, Shield, and control-plane write tools are separate, explicit runtime or authenticated operations. Credential references are names, not secret values; recorded relationships do not prove exploitation or successful data access. See the permission and network boundaries before enabling cloud scans or outbound integrations.
Supported sources
Discovery and scanning read from these sources today; the last row lists where evidence can be sent. The list is generated from a code-backed manifest (docs/images/integrations-manifest.json); a test fails if it names anything without an implementation.
| Area | Integrations |
|---|---|
| AI clients + IDEs | Claude, Codex, Cursor, GitHub Copilot, Windsurf, Cortex Code, Gemini CLI, JetBrains AI, Junie, Amazon Q, Cline, Roo Code, Continue, Zed, Goose, Snowflake CLI, Docker MCP Toolkit, Tabnine, Sourcegraph Cody, Aider, Void, Aide, Trae, Pieces, OpenClaw, mcp-cli |
| AI platforms + model hubs | OpenAI, Hugging Face, Ollama, MLflow, W&B, Langfuse, LangSmith |
| GPU + neo clouds | CoreWeave, Nebius, Lambda, RunPod, Vast.ai, Crusoe, GPU containers + K8s GPU nodes |
| Hyperscalers + Kubernetes | AWS, Azure, GCP, Kubernetes |
| Data + vector stores | Snowflake, Databricks, Supabase, Pinecone, Qdrant, Weaviate, Chroma, Milvus |
| Identity + SaaS + dev | Okta, GitHub Actions, Vercel, Microsoft Entra ID, Jira, ServiceNow, Slack, Jamf |
| Evidence out | ClickHouse, BigQuery, S3, GCS, Azure Blob, Jira tickets, Slack alerts, Vanta, Drata, OCSF syslog |
Product names and logos are trademarks of their owners, used only to identify supported evidence sources. Their use does not imply endorsement or partnership.
How the data moves
Blast radius
Links
Metadata
Release files for agent-bom 0.115.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agent_bom-0.115.3.tar.gz | 13.8 MB | With provenance | Details for agent_bom-0.115.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_bom-0.115.3-py3-none-any.whl | Python 3 | none | any | Details for agent_bom-0.115.3-py3-none-any.whl |
Total release size: 24.7 MB
Release files / agent_bom-0.115.3.tar.gz
| Download URL | agent_bom-0.115.3.tar.gz |
|---|---|
| Size | 13.8 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fd58dece30e1ce38a50974f2572ce2e9573ee1718f97410d2685894c32127fbd
|
|
BLAKE2b-256 checksum How to use checksums |
0b13c3f75c6bfe72031e1c0edf866a19f205ce26a740d785289c3dc5fad9adc7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.
Transparency logRelease files / agent_bom-0.115.3-py3-none-any.whl
| Download URL | agent_bom-0.115.3-py3-none-any.whl |
|---|---|
| Size | 10.9 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f45e9545f8e5d95a1efe50b982248e6c79411d67bc3fd1819edb04e03842e7e9
|
|
BLAKE2b-256 checksum How to use checksums |
19f29c3ec59170af9c301e20c294266cd997d312650bbab92b447f61602b819e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.
Transparency logSecurity for agent-bom 0.115.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for agent_bom-0.115.3.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 16, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.