agentleFS
Hack23Hack23/European-Parliament-MCP-Server/.github/skills/gdpr-compliance/SKILL.md

gdpr-compliance

Skill30 starsChanged 9 months agoApache-2.0View on GitHub

GDPR and data protection patterns for handling European Parliament personal data with privacy by design

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Data Minimization: Only collect necessary personal data fields

    line 25
  2. Distinctive:

    Purpose Limitation: Use data only for stated purpose (parliamentary information)

    line 26
  3. Distinctive:

    Transparency: Document all data processing activities

    line 34

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GDPR Compliance Skill

Context

This skill applies when:

  • Processing personal data from European Parliament (MEP information)
  • Implementing data minimization strategies
  • Supporting GDPR rights (access, rectification, erasure)
  • Implementing audit logging for personal data access
  • Designing privacy-by-design features
  • Handling data retention and deletion
  • Implementing consent mechanisms
  • Creating data protection impact assessments

GDPR (EU Regulation 2016/679) applies to all processing of EU citizens' personal data. Even though MEP data is public, GDPR principles still apply.

Rules

  1. Data Minimization: Only collect necessary personal data fields
  2. Purpose Limitation: Use data only for stated purpose (parliamentary information)
  3. Storage Limitation: Cache personal data for max 24 hours
  4. Accuracy: Maintain data integrity, support corrections
  5. Lawful Basis: Public interest (GDPR Art. 6(1)(e)) for MEP data
  6. Audit Logging: Log all personal data access
  7. Right to Rectification: Support data correction requests
  8. Right to Erasure: Limited for public figures (GDPR Art. 17(3)(e))
  9. Data Protection by Design: Build privacy into architecture
  10. Transparency: Document all data processing activities

Examples

✅ Good Pattern: Data Minimization

// GOOD: Only public information
interface MEPPublicData {
  id: number;
  fullName: string;
  country: string;
  partyGroup: string;
  active: boolean;
  // DO NOT collect: private addresses, personal phones, family data
}

// Define data purpose
const DATA_PURPOSE = 'Providing public parliamentary information via MCP protocol';

✅ Good Pattern: Audit Logging

/**
 * GDPR-compliant audit logging
 * Requirement: GDPR Art. 30 (Records of processing activities)
 */
function logPersonalDataAccess(
  actor: string,
  subject: string,
  purpose: string
): void {
  auditLog.record({
    timestamp: new Date().toISOString(),
    eventType: 'personal_data_access',
    actor,
    subject,
    purpose,
    legalBasis: 'GDPR_Art_6_1_e_Public_Interest',
  });
}

// Usage
logPersonalDataAccess(
  'mcp_client',
  'mep:12345',
  'Parliamentary information query'
);

✅ Good Pattern: Right to Rectification

/**
 * Support GDPR Art. 16 (Right to rectification)
 */
async function updateMEPData(
  id: number,
  corrections: Partial<MEP>
): Promise<void> {
  // Validate corrections
  const validated = MEPUpdateSchema.parse(corrections);
  
  // Update data
  await updateMEP(id, validated);
  
  // Invalidate cache
  invalidateMEPCache(id);
  
  // Audit log
  auditLog.record({
    eventType: 'data_rectification',
    subject: `mep:${id}`,
    action: 'update',
    details: corrections,
    legalBasis: 'GDPR_Art_16_Right_to_Rectification',
  });
}

✅ Good Pattern: Storage Limitation

/**
 * GDPR Art. 5(1)(e): Storage limitation
 * Personal data cached for max 24 hours
 */
const mepCache = new LRUCache<string, MEP>({
  max: 1000,
  ttl: 1000 * 60 * 60 * 24, // 24 hours max
  allowStale: false,
});

// Auto-purge expired entries
setInterval(() => {
  mepCache.purgeStale();
}, 1000 * 60 * 60); // Hourly cleanup

Anti-Patterns

❌ Bad: No Audit Logging

// NEVER - GDPR requires audit logs!
async function bad(mepId: number) {
  return await getMEP(mepId); // No logging!
}

❌ Bad: Excessive Data Collection

// NEVER - violates data minimization!
interface MEPBad {
  id: number;
  fullName: string;
  privateAddress: string;      // Excessive!
  personalPhone: string;        // Excessive!
  familyMembers: string[];      // Excessive!
  medicalRecords: string;       // Excessive!
}

❌ Bad: Indefinite Storage

// NEVER - violates storage limitation!
const cache = new Map(); // No TTL = indefinite storage!

GDPR Rights Implementation

Right to Access (Art. 15)

async function getPersonalData(mepId: number): Promise<PersonalDataExport> {
  return {
    data: await getMEP(mepId),
    purpose: DATA_PURPOSE,
    legalBasis: 'Public interest (Art. 6(1)(e))',
    retentionPeriod: '24 hours (cache)',
    recipients: 'MCP clients',
  };
}

Right to Erasure (Art. 17)

async function handleErasureRequest(mepId: number): Promise<ErasureResult> {
  // For current MEPs: Cannot erase (public interest exemption)
  // CAN erase: Cached personal contact information
  
  invalidateMEPCache(mepId);
  
  return {
    success: true,
    scope: 'cached_data_only',
    reason: 'Public figure exemption (GDPR Art. 17(3)(e))',
  };
}

ISMS Compliance

  • PR-001: Privacy by Design and Default (GDPR Art. 25)
  • PR-002: Data Minimisation (GDPR Art. 5(1)(c))
  • PR-003: Data Subject Rights (GDPR Art. 15–22)
  • AU-002: Audit Logging for personal-data access
  • SC-001: Transport security (TLS 1.3) for all personal-data flows

Policy References

Primary: Privacy Policy

Related policies:

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.