Skip to content

Gibs MCP Server — EU regulatory compliance for AI agents (AI Act, GDPR, DORA)

Notifications You must be signed in to change notification settings

buildsyncinc/gibs-mcp

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

Gibs MCP Server

License: MIT

Regulatory compliance for AI-powered development tools — classify AI systems, check obligations, and get article-level citations across 240+ articles and 3 major regulations.

Full Documentation · Get API Key · API Reference


Overview

Gibs MCP Server connects your AI development environment directly to a regulatory compliance knowledge base. Currently covering:

Regulation Scope Articles
EU AI Act AI system classification, prohibited practices, obligations by risk level 113 articles + 13 annexes
GDPR Data protection, processing obligations, data subject rights 99 articles
DORA ICT risk management, incident reporting, third-party oversight for financial entities 64 articles + 12 delegated/implementing acts

Every response includes article-level citations to binding legal text, with real-time corpus updates as regulations evolve.


Quick Start

1. Get an API Key

Sign up at gibs.dev and grab your API key from the dashboard.

2. Connect via Claude Desktop

Add this to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "gibs": {
      "url": "https://mcp.gibs.dev/sse"
    }
  }
}

3. Authenticate

Pass your API key as the user_api_key parameter when calling any tool, or set it in your environment:

export GIBS_API_KEY=your_api_key_here

Tools

classify_ai_system

Classify an AI system under AI Act risk levels (unacceptable, high-risk, limited, minimal) with full legal reasoning.

Parameter Type Required Description
description string Yes What the AI system does (10–5000 chars)
data_types list[string] No Types of data processed (e.g., ["biometric", "personal"])
decision_scope string No What decisions the system influences
sector string No Industry sector (e.g., "healthcare", "finance", "hr")

Example prompt:

Classify my facial recognition attendance system for schools

What you get back:

  • Risk classification (e.g., high-risk under Annex III, point 1(a))
  • Specific Article 6 analysis with Annex III cross-references
  • Applicable obligations based on classification
  • Relevant exemptions or exceptions, if any

check_compliance

Ask any regulatory compliance question and get a structured answer with article-level citations.

Parameter Type Required Description
question string Yes Compliance question (10–2000 chars)
system_description string No Context about your AI system or organization
regulation string No Target regulation: "ai_act", "gdpr", "dora", or "both" (default: "both")

Example prompts:

What are the GDPR requirements for a data breach notification?

Returns Article 33 (notification to supervisory authority) and Article 34 (communication to data subjects) obligations, including the 72-hour notification timeline, required content, and exceptions.

Does DORA apply to a fintech startup processing payments?

Returns Article 2 scope analysis with financial entity classification, applicable ICT risk management obligations, and relevant delegated act requirements.


health_check

Check if the compliance API is available. No parameters required.


Usage Examples

1. AI System Classification

You: Classify my facial recognition attendance system for schools

Gibs: This system is classified as HIGH-RISK under the EU AI Act.

- Article 6(2) read with Annex III, point 1(a): biometric identification
  and categorisation of natural persons
- As used in an educational context, also caught by Annex III, point 3(a):
  AI systems intended to be used to determine access to educational institutions

Obligations include:
- Risk management system (Article 9)
- Data governance (Article 10)
- Technical documentation (Article 11)
- Record-keeping (Article 12)
- Transparency to users (Article 13)
- Human oversight (Article 14)
- Accuracy, robustness, cybersecurity (Article 15)
- Conformity assessment before placing on market (Article 43)

2. GDPR Data Breach Obligations

You: What are the GDPR requirements for a data breach notification?

Gibs: GDPR imposes two notification obligations following a personal data breach:

1. Notification to supervisory authority — Article 33
   - Without undue delay and no later than 72 hours after becoming aware
   - Must include: nature of breach, categories and approximate number of
     data subjects, likely consequences, measures taken or proposed
   - Exception: unlikely to result in a risk to rights and freedoms

2. Communication to data subjects — Article 34
   - Required when breach is likely to result in a HIGH risk
   - Must describe in clear and plain language the nature of the breach
   - Not required if: appropriate technical safeguards applied (e.g.,
     encryption), subsequent measures taken that eliminate the high risk,
     or it would involve disproportionate effort (use public communication instead)

The controller must also document all breaches per Article 33(5), regardless
of whether they meet the notification threshold.

3. DORA Scope Analysis

You: Does DORA apply to a fintech startup processing payments?

Gibs: Yes. Under Article 2(1), DORA applies to payment institutions as
defined in Directive 2015/2366 (PSD2), which includes entities authorized
to provide payment services.

As a financial entity under DORA, the startup must comply with:
- ICT risk management framework (Chapter II, Articles 5–16)
- ICT-related incident management and reporting (Chapter III, Articles 17–23)
- Digital operational resilience testing (Chapter IV, Articles 24–27)
- ICT third-party risk management (Chapter V, Articles 28–44)
- Information-sharing arrangements (Chapter VI, Article 45)

Note: Proportionality applies — Article 4 allows competent authorities to
consider the size, risk profile, and complexity of the financial entity when
assessing compliance.

Connection Details

SSE Endpoint https://mcp.gibs.dev/sse
Protocol Model Context Protocol (MCP) over Server-Sent Events
Authentication API key from gibs.dev dashboard

Supported Clients

Any MCP-compatible client can connect to the Gibs server. Tested with:


Links


License

MIT License. See LICENSE for details.


Built by Gibbr AB — making regulatory compliance accessible for developers.

About

Gibs MCP Server — EU regulatory compliance for AI agents (AI Act, GDPR, DORA)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •