Skip to main content

AI Bill of Materials (AI-BOM) generator + auditor MCP — CycloneDX ML-BOM, SPDX 3.0 AI profile, EU AI Act Annex IV mapping, NIST AI RMF alignment, US EO 14028 federal procurement. By MEOK AI Labs.

Project description

ai-bom-mcp MCP server

PyPI Downloads GitHub stars License: MIT

AI Bill of Materials MCP

Generate and audit AI Bills of Materials for EU AI Act Annex IV, US EO 14028, NIST AI RMF, and ISO 42001. CycloneDX-compatible output.

MEOK AI Labs

Install · Tools · Pricing · Attestation API


Why This Exists

AI Bills of Materials (AI-BOMs) are becoming mandatory. EU AI Act Annex IV requires high-risk AI providers to document training data, model architecture, evaluation metrics, and deployment constraints. US Executive Order 14028 requires software supply chain transparency for federal procurement. NIST and ISO 42001 both reference BOM-style documentation.

No standard format exists yet. CycloneDX has proposed an ML-BOM extension, SPDX is exploring AI metadata, and the EU AI Office is developing Annex IV templates. This MCP generates structured AI-BOMs that satisfy all four frameworks, audits existing BOMs for completeness, and maps required fields to specific regulatory articles.

Install

pip install ai-bom-mcp

Tools

Tool Regulation Reference What it does
generate_ai_bom Annex IV, EO 14028, NIST, ISO 42001 Generate a structured AI Bill of Materials
audit_ai_bom_completeness All frameworks Audit an existing AI-BOM for missing required fields
map_to_regulation EU AI Act / EO 14028 / NIST / ISO 42001 Map AI-BOM fields to specific regulatory requirements
required_fields All frameworks List all required BOM fields per regulation

Example

Prompt: "Generate an AI-BOM for our fraud detection model. It uses
XGBoost trained on 2M transactions from our data warehouse, deployed
as a REST API in AWS eu-west-1, with weekly retraining."

Result: Structured AI-BOM with: model card (XGBoost, version, hyperparams),
training data provenance (2M records, internal data warehouse, no PII
confirmed), deployment spec (REST API, eu-west-1, auto-scaling),
monitoring (weekly retrain, drift detection status), regulatory mapping
(Annex IV sections covered, EO 14028 SBOM requirements met, NIST AI RMF
MAP subcategories addressed). Completeness score with gaps flagged.

Pricing

Tier Price What you get
Free £0 10 calls/day — BOM generation + field listing
Pro £199/mo Unlimited + HMAC-signed attestations + verify URLs
Enterprise £1,499/mo Multi-tenant + co-branded reports + webhooks

Subscribe to Pro · Enterprise

Attestation API

Every Pro/Enterprise audit produces a cryptographically signed certificate:

POST https://meok-attestation-api.vercel.app/sign
GET  https://meok-attestation-api.vercel.app/verify/{cert_id}

Zero-dep verifier: pip install meok-attestation-verify

Links

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_bom_mcp-1.0.1.tar.gz (10.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ai_bom_mcp-1.0.1-py3-none-any.whl (9.7 kB view details)

Uploaded Python 3

File details

Details for the file ai_bom_mcp-1.0.1.tar.gz.

File metadata

  • Download URL: ai_bom_mcp-1.0.1.tar.gz
  • Upload date:
  • Size: 10.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for ai_bom_mcp-1.0.1.tar.gz
Algorithm Hash digest
SHA256 ac431a0b5357d796057209f1b5884497d68c0a22dd9afc9a6044aecf75851818
MD5 3cc278f92110097810ccc9323c0570c9
BLAKE2b-256 c7908ff1dedcf3f21e3ffd41008ef5b53dbffd4bf0d0579d9ff0a92e6c6e85bf

See more details on using hashes here.

File details

Details for the file ai_bom_mcp-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: ai_bom_mcp-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 9.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for ai_bom_mcp-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d4be912f11ce9d3040349bc72676578fa456b14a764ab953d1ce085b16496780
MD5 2698d034edde68743a8d345dc0513c09
BLAKE2b-256 8f3a930eac754737c3d7dcc16f4625fa7b3abc71ef36ad87fa77a857bf334e6b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page