Skip to main content
Glama
CRA Compliance MCP

CRA Compliance MCP

Pro turns every result into an HMAC-signed attestation with a public verify URL your auditor validates without an account โ€” EU AI Act Art 11/12 ready. โ†’ Start: https://proofof.ai ยท pip install meok-attestation-verify to verify any cert.

MCP Scorecard: 90/100

Cra Compliance MCP

MEOK AI Labs PAYG enabled GSPC License PyPI

EU Cyber Resilience Act (Reg 2024/2847) compliance MCP for products with digital elements

EU Cyber Resilience Act (Reg 2024/2847) compliance MCP for products with digital elements. CE marking, vulnerability disclosure, SBOM. MIT


๐Ÿš€ Quick Start

# Install via pip
pip install cra_compliance_mcp

# Or install via Smithery
npx -y @smithery/cli@latest install cra-compliance-mcp --client claude

Related MCP server: EU AI Act Compliance MCP

โšก Pay-per-call (PAYG) โ€” no subscription

This MCP supports universal pay-per-call billing across the MEOK compliance fleet:

# One-time setup
export MEOK_PAYG_KEY="your_topup_token"

# Every tool call now deducts ยฃ0.05 from your balance.
# When balance hits zero, the tool returns a top-up URL.
# Works across all 7 MEOK compliance MCPs with the same token.
  • No subscription โ€” top up once, deduct per call.

  • ยฃ0.05/call default (configurable via MEOK_PAYG_RATE_GBP).

  • USDC on Base L2 accepted โ€” set MEOK_X402_RECEIVER and pay via stablecoin.

  • Backward-compatible โ€” when MEOK_PAYG_KEY is unset, behaviour is unchanged.

Get a token: councilof.ai/payg (ยฃ10 / ยฃ50 / ยฃ200 top-up tiers).

โœจ Features

  • MCP protocol compliant

  • Easy installation

  • Well-documented API

  • Production-ready

  • Active maintenance

๐Ÿ“– Documentation

๐Ÿ›ก๏ธ Compliance

This MCP server is built with EU AI Act compliance built-in:

  • โœ… Article 9 โ€” Risk Management System

  • โœ… Article 13 โ€” Transparency & Instructions for Use

  • โœ… Article 15 โ€” Bias Detection & Testing

  • โœ… Article 26 โ€” FRIA Support (where applicable)

  • โœ… Article 50 โ€” AI Content Watermarking (where applicable)

Need help getting compliant? Book a free 15-min diagnostic โ†’

How MEOK charges

MEOK has no subscriptions and no tiers. You pay per job, and only when the agreed artifact has been delivered to you. There is no public price list. See https://meok.ai/pricing.

This repository's source is MIT-licensed and free to self-host.

๐Ÿค Part of the MEOK Ecosystem

This server is part of the MEOK AI Labs ecosystem โ€” 26 PyPI packages ยท ~16,300 monthly installs.

Domain

Purpose

councilof.ai

EU AI Act compliance marketplace

safetyof.ai

AI safety & monitoring

meok.ai

Sovereign AI platform

cobolbridge.ai

Legacy modernization

๐Ÿ“œ License

MIT ยฉ CSOAI-ORG


Configuration

Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:

{
  "mcpServers": {
    "cra-compliance-mcp": {
      "command": "uvx",
      "args": ["cra-compliance-mcp"]
    }
  }
}

Or: pip install cra-compliance-mcp then run the cra-compliance-mcp command (stdio transport).

Examples

Once configured, ask your assistant, for example:

  • "Use classify_product to โ€ฆ"

  • "Use audit_annex_i to โ€ฆ"

  • "Use sbom_skeleton to โ€ฆ"

Available Tools

7 tools
audit_annex_iA

Audit Annex I essential cybersecurity requirements (both Part 1 product properties and Part 2 vulnerability handling) against your current controls.

Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: product_description (str): The product description to analyze or process. current_controls (str): The current controls to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent โ€” calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: product_description (required), current_controls, api_key. Returns: result

classify_productA

Classify a product with digital elements (PDE) into its CRA class (default/I/II/critical) and return the conformity assessment path + essential requirements scope.

Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: product_description (str): The product description to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent โ€” calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: product_description (required), api_key. Returns: result

conformity_assessment_roadmapA

Produce a conformity assessment roadmap for CE marking your product under CRA.

Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: product_class (str): The product class to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent โ€” calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: product_class (required), api_key. Returns: result

enforcement_statusA

Current CRA enforcement timeline + key deadlines.

Behavior: This tool is read-only and stateless โ€” it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent โ€” calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: api_key. Returns: result

sbom_skeletonA

Generate a minimal CycloneDX-style SBOM skeleton required for CRA Article 13. Pass components as a comma-separated list or JSON; Pro tier auto-scans dependencies.

Behavior: This tool generates structured output without modifying external systems. Output is deterministic for identical inputs. No side effects. Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: product_name (str): The product name to analyze or process. components (str): The components to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent โ€” calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: product_name (required), components, api_key. Returns: result

sign_cra_attestationA

Generate a cryptographically signed CRA (Cyber Resilience Act) compliance attestation (Pro/Enterprise).

Uses the shared MEOK attestation module โ€” HMAC-SHA256 signed JSON + public verify URL

  • optional board-ready PDF. Auditors validate via verify_url without backend access. Expires 365 days from issue.

  • findings_csv: comma-separated findings (e.g. "Annex I.1 cybersecurity-by-design PASS,Annex I.2 vulnerability handling GAP")

  • requirements_audited_csv: comma-separated Annex I requirement IDs (e.g. "1,2,3")

  • include_pdf_base64: True to receive PDF as base64

Inputs: entity_name (required), overall_score (required), findings_csv, requirements_audited_csv, +2 more. Returns: result

vulnerability_reporting_readinessA

Check readiness for the Sep 2026 mandatory reporting of exploited vulnerabilities + severe incidents under CRA Article 14 (single reporting platform via ENISA).

Behavior: This tool is read-only and stateless โ€” it produces analysis output without modifying any external systems, databases, or files. Safe to call repeatedly with identical inputs (idempotent). Free tier: 10/day rate limit. Pro tier: unlimited. No authentication required for basic usage.

When to use: Use this tool when you need to assess, audit, or verify compliance requirements. Ideal for gap analysis, readiness checks, and generating compliance documentation.

When NOT to use: Do not use as a substitute for qualified legal counsel. This tool provides technical compliance guidance, not legal advice.

Args: product_description (str): The product description to analyze or process. api_key (str): The api key to analyze or process.

Behavioral Transparency: - Side Effects: This tool is read-only and produces no side effects. It does not modify any external state, databases, or files. All output is computed in-memory and returned directly to the caller. - Authentication: No authentication required for basic usage. Pro/Enterprise tiers require a valid MEOK API key passed via the MEOK_API_KEY environment variable. - Rate Limits: Free tier: 10 calls/day. Pro tier: unlimited. Rate limit headers are included in responses (X-RateLimit-Remaining, X-RateLimit-Reset). - Error Handling: Returns structured error objects with 'error' key on failure. Never raises unhandled exceptions. Invalid inputs return descriptive validation errors. - Idempotency: Fully idempotent โ€” calling with the same inputs always produces the same output. Safe to retry on timeout or transient failure. - Data Privacy: No input data is stored, logged, or transmitted to external services. All processing happens locally within the MCP server process.

Inputs: product_description (required), api_key. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A4.2/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool serves a distinct compliance function (audit, classification, roadmap, timeline, SBOM, attestation, reporting readiness) with no overlapping purposes, making it easy for agents to select the correct tool.

    Naming Consistency3/5

    All names use underscore_separated words but mix verb-noun (e.g., audit_annex_i) and noun-noun patterns (e.g., enforcement_status, sbom_skeleton), showing moderate inconsistency.

    Tool Count5/5

    7 tools is appropriate for a compliance server covering classification, auditing, roadmap, timelines, SBOM, attestation, and reporting readiness without being overwhelming or insufficient.

    Completeness4/5

    The tool set covers the main CRA requirements (classification, auditing, roadmap, enforcement info, SBOM, attestation, reporting readiness). A minor gap is the lack of a dedicated vulnerability handling audit tool, but Annex I audit covers it partially.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers