MCP.Market

Compliance Shield MCP server

by mdfifty50-boop·io.github.mdfifty50-boop/compliance-shield·v0.1.3
No reviews yet

ZATCA, UAE CT, EU AI Act regulatory compliance for AI agents

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars60 downloads/wk

Reviews

Write one

Nobody has reviewed Compliance Shield yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Compliance Shield tools (6, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • assess_risk_level

    Classify an AI system under the EU AI Act risk framework (Unacceptable, High, Limited, Minimal). Returns required obligations and article references.

  • check_compliance_gaps

    Identify missing EU AI Act compliance requirements for an audit trail. Checks human oversight, decision logging, reasoning documentation, model identification, and responsible person assignment.

  • create_audit_trailwrite action

    Start a new compliance audit trail for an AI system. Returns a trail_id used for all subsequent logging and compliance checks.

  • generate_evidence_package

    Generate an auditor-ready evidence package with system info, decision log summary, human oversight statistics, model usage breakdown, and compliance status. Suitable for regulatory submission.

  • get_enforcement_timeline

    Show upcoming EU AI Act enforcement deadlines with days remaining. Includes penalty structure for violations (up to 35M EUR / 7% global turnover).

  • log_decision

    Log an AI decision with full traceability — input, output, reasoning, human oversight status, model used, and confidence. Each entry is timestamped and auto-numbered.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan12 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 156 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Compliance Shield compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 48,255 servers
Tools
6
the typical server has 7
Tools that change things
17%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
60
more than 49% of 12,191 servers with a package

What its tools let an agent do: 4 read · 2 create

Install Compliance Shield in Claude Code, Cursor or VS Code

Runs npx -y compliance-shield-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add compliance-shield -- npx -y compliance-shield-mcp
Add to Cursor

What the publisher says

From the Compliance Shield repository's README, as published. We do not edit it. Read it on GitHub

compliance-shield-mcp

EU AI Act compliance audit trails and evidence generation for AI agent systems.

EU AI Act enforcement begins August 2, 2026. Fines up to 35M EUR or 7% of global annual turnover.

What it does

Runtime compliance layer that plugs into any MCP-compatible AI system to provide:

  • Risk Classification — Classify AI systems as Unacceptable, High, Limited, or Minimal risk per the EU AI Act framework
  • Audit Trails — Create and maintain decision logs with full traceability (input, output, reasoning, human oversight, model, confidence)
  • Gap Analysis — Identify missing compliance requirements with specific article references and actionable recommendations
  • Evidence Packages — Generate auditor-ready documentation suitable for regulatory submission
  • Enforcement Timeline — Track upcoming deadlines with days remaining and penalty structure

Install

npx compliance-shield-mcp

Claude Desktop

{
  "mcpServers": {
    "compliance-shield": {
      "command": "npx",
      "args": ["compliance-shield-mcp"]
    }
  }
}

Tools

Resources

Quick Start

1. assess_risk_level → Know your risk classification
2. create_audit_trail → Start logging
3. log_decision (repeatedly) → Record every AI decision
4. check_compliance_gaps → Find what's missing
5. generate_evidence_package → Hand to your auditor

EU AI Act Key Dates

Architecture

  • Pure Node.js, ES modules
  • @modelcontextprotocol/sdk + zod only
  • In-memory Maps (no external dependencies)
  • stdio transport

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Compliance Shield: common questions

Is Compliance Shield MCP server safe?
Mostly: it is graded B (78/100). Read the Compliance Shield safety report
How do I install Compliance Shield?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Compliance Shield need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Compliance Shield maintained?
The last commit was 194 days ago (2026-04-24). The latest release is v0.1.3.
How does Compliance Shield compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); tools 6 (the typical server has 7); tools that change things 17% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from mdfifty50-boop →