io.github.vdineshk/ai-compliance-monitor

Official4 tools

by vdineshk · TypeScript

Regulatory intelligence for AI agents across jurisdictions

Delivers regulatory intelligence for AI agents across multiple jurisdictions.

Captured live from the server via tools/list.

check_obligations

Given an AI agent use case and optional jurisdiction, returns all applicable regulatory obligations with evidence requirements, enforcement dates, and penalty information. Use this to understand what compliance requirements apply to a specific type of AI agent.

Parameters (2)

use_casestringrequired
The AI agent use case to check. Examples: hiring_screening, credit_scoring, customer_service, content_moderation, medical_triage, autonomous_coding, financial_trading
jurisdiction_codestring
Optional jurisdiction code to filter by. Examples: EU, SG, US-CO. Omit to get all jurisdictions.

get_regulation_articles

Returns structured, machine-readable regulation details including specific articles, obligation classifications, risk levels, and evidence requirements. Use this to understand the detailed requirements of a specific regulation.

Parameters (2)

regulation_idstringrequired
The regulation identifier. Options: eu-ai-act, sg-imda-agentic, co-ai-act
categorystring
Optional filter by obligation category. Options: transparency, record_keeping, human_oversight, risk_assessment, incident_reporting, data_governance, monitoring, audit

check_deadline

Returns upcoming and recent compliance deadlines with enforcement dates, penalty information, and related obligations. Use this to understand time-sensitive compliance requirements.

Parameters (3)

jurisdiction_codestring
Optional jurisdiction code to filter by. Examples: EU, SG, US-CO
include_passedboolean
Whether to include deadlines that have already passed. Default: false
months_aheadnumber
Number of months ahead to look for upcoming deadlines. Default: 12

compare_jurisdictions

Side-by-side comparison of regulatory obligations across jurisdictions for a given compliance category. Shows equivalent, overlapping, stricter, and weaker mappings between regulations. Use this to understand how requirements differ across borders.

Parameters (2)

categorystringrequired
The obligation category to compare. Options: transparency, record_keeping, human_oversight, risk_assessment, incident_reporting, data_governance, monitoring, audit
jurisdictionsarray
Optional list of jurisdiction codes to compare. Default: all available. Examples: ["EU", "SG", "US-CO"]

README.md4 KBView on GitHub

AI Compliance Monitor

Structured regulatory intelligence for AI agents operating across jurisdictions.

The first MCP server purpose-built for AI agent compliance. Check obligations, deadlines, and cross-jurisdiction requirements for the EU AI Act, Singapore IMDA Agentic AI Framework, and Colorado AI Act.

Why This Exists

AI agents operating across borders face a fragmented regulatory landscape. The EU AI Act requires automatic logging (Article 12). Singapore's IMDA framework mandates escalation protocols. Colorado demands impact assessments. No existing tool maps agent behavior to specific regulatory requirements across jurisdictions.

This server provides machine-readable, structured regulatory intelligence that AI agents can query at runtime to understand their compliance obligations.

MCP Tools

Tool	Description
`check_obligations`	Given an agent use case + jurisdiction → applicable requirements
`get_regulation_articles`	Structured regulation details with evidence requirements
`check_deadline`	Enforcement dates, penalties, compliance milestones
`compare_jurisdictions`	Side-by-side obligation comparison across regulations

Quick Start

Connect via MCP

code

Server URL: https://ai-compliance-monitor.sgdata.workers.dev/mcp

REST API

bash

# Check obligations for a hiring agent
curl "https://ai-compliance-monitor.sgdata.workers.dev/api/obligations?use_case=hiring_screening"

# Get EU AI Act requirements
curl "https://ai-compliance-monitor.sgdata.workers.dev/api/regulations?regulation_id=eu-ai-act"

# Check upcoming deadlines
curl "https://ai-compliance-monitor.sgdata.workers.dev/api/deadlines"

# Compare transparency requirements across jurisdictions
curl "https://ai-compliance-monitor.sgdata.workers.dev/api/compare?category=transparency"

# Service stats
curl "https://ai-compliance-monitor.sgdata.workers.dev/api/stats"

Regulatory Coverage

Regulation	Jurisdiction	Status	Key Deadline
EU AI Act	European Union	Active	Aug 2, 2026 (high-risk)
IMDA Agentic AI Framework	Singapore	Active (voluntary)	Published Jan 2026
Colorado AI Act (SB 24-205)	Colorado, US	Active	Feb 1, 2026 (enforced)

Use Cases Covered

Hiring/recruitment screening
Credit scoring
Customer service agents
Content moderation
Medical triage
Autonomous coding agents
Financial trading agents

Deployment (Self-Host)

Prerequisites

Cloudflare account with Workers enabled
Wrangler CLI (npm install -g wrangler)
CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID environment variables

Deploy

bash

# Clone the repo
git clone https://github.com/vdineshk/ai-compliance-monitor.git
cd ai-compliance-monitor

# Install dependencies
npm install

# Create D1 database
npx wrangler d1 create ai-compliance-monitor-db
# Copy the database_id from output into wrangler.toml

# Run migrations
npx wrangler d1 migrations apply ai-compliance-monitor-db --remote

# Seed regulatory data
npx wrangler d1 execute ai-compliance-monitor-db --remote --file=./migrations/0002_seed_data.sql

# Deploy
npx wrangler deploy

Dry Run (verify free-tier compliance)

bash

npx wrangler deploy --dry-run

Data Model

Regulations: Top-level regulatory frameworks (EU AI Act, IMDA, Colorado)
Obligations: Specific requirements within each regulation, classified by category
Deadlines: Enforcement dates with penalty information
Obligation Mappings: Cross-jurisdiction equivalence mappings
Use Case Obligations: Maps agent use cases to applicable obligations

Part of the Dominion Agent Economy Engine

This server feeds behavioral interaction data to the Dominion Observatory, the trust scoring layer for the AI agent economy.

License

MIT

Contact

Built by @vdineshk | Singapore

Install

claude_desktop_config.json

{
  "mcpServers": {
    "ai-compliance-monitor": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://ai-compliance-monitor.sgdata.workers.dev/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.