DORA Compliance MCP
It's a read-only DORA (EU 2022/2554) compliance toolkit that classifies financial entities and ICT incidents, audits the five DORA pillars, and generates readiness and attestation outputs.
Classify entities (
classify_entity) — determines DORA applicability, entity type, proportionality tier, and starting pillars from a description.List pillars (
list_pillars) — enumerates the 5 DORA pillars with article ranges and key obligations.Audit a single pillar (
audit_pillar) — checks one pillar (1–5) against your current controls and returns pass/fail per obligation, gap list, and remediation priority.Audit all pillars (
audit_all_pillars) — runs the full 5-pillar audit with an executive summary.Classify incidents (
classify_incident) — tests an ICT incident against major-incident thresholds (Delegated Reg. 2024/1772) to decide if 4h/72h/1-month reporting applies.Register of Information template (
register_of_information_template) — returns the Article 28.3 annual submission structure.TLPT readiness (
tlpt_readiness) — assesses Article 26 threat-led penetration testing scope and TIBER-EU gaps.Signed certificates (
get_dora_certificate) — issues an HMAC-SHA256 signed attestation with verify URL and optional PDF (Pro/Enterprise).Enforcement tracker (
enforcement_status) — current DORA enforcement state and upcoming deadlines.Operational notes — stateless/idempotent, no side effects, local in-memory processing; free tier 10 calls/day, optional £0.05/call PAYG billing.
Verification is free and public: signed measurement cards and live verification at https://councilof.ai — measurement, not certification.
Dora Compliance MCP
DORA (Regulation EU 2022/2554) compliance MCP for financial entities
DORA (Regulation EU 2022/2554) compliance MCP for financial entities. ICT risk, incident classification, reporting workflows. MIT
🚀 Quick Start
# Install via pip
pip install dora_compliance_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install dora-compliance-mcp --client claudeRelated MCP server: EU AI Act Compliance MCP
⚡ Pay-per-call (PAYG) — 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 £0.05 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 — top up once, deduct per call.
£0.05/call default (configurable via
MEOK_PAYG_RATE_GBP).USDC on Base L2 accepted — set
MEOK_X402_RECEIVERand pay via stablecoin.Backward-compatible — when
MEOK_PAYG_KEYis unset, behaviour is unchanged.
Get a token: councilof.ai/payg (£10 / £50 / £200 top-up tiers).
✨ Features
MCP protocol compliant
Easy installation
Well-documented API
Production-ready
Active maintenance
📖 Documentation
🛡️ Compliance
This MCP server is built with EU AI Act compliance built-in:
✅ Article 9 — Risk Management System
✅ Article 13 — Transparency & Instructions for Use
✅ Article 15 — Bias Detection & Testing
✅ Article 26 — FRIA Support (where applicable)
✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
🏢 Enterprise
Need custom development, SLA guarantees, or white-label deployment?
View Pricing → | Contact Sales →
🤝 Part of the MEOK Ecosystem
This server is part of the Council of AI ecosystem — 26 PyPI packages · ~public measurement tools.
Domain | Purpose |
EU AI Act compliance marketplace | |
AI safety & monitoring | |
Sovereign AI platform | |
Legacy modernization |
📜 License
MIT © CSOAI-ORG
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"dora-compliance-mcp": {
"command": "uvx",
"args": ["dora-compliance-mcp"]
}
}
}Or: pip install dora-compliance-mcp then run the dora-compliance-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
"Use
classify_entityto …""Use
list_pillarsto …""Use
audit_pillarto …"
Available Tools
9 toolsaudit_all_pillarsA
Run audits across all 5 DORA pillars and return an executive summary.
Behavior: This tool is read-only and stateless — 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: entity_description (str): The entity 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 — 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: entity_description (required), current_controls, api_key. Returns: result
audit_pillarA
Audit a specific DORA pillar (1-5) against your entity's current controls. Returns per-obligation pass/fail + gap list + remediation priority.
Behavior: This tool is read-only and stateless — 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: pillar_number (int): The pillar number to analyze or process. entity_description (str): The entity 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 — 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: pillar_number (required), entity_description (required), current_controls, api_key. Returns: result
classify_entityB
Classify a financial entity's DORA applicability + which entity type it is. Returns in-scope status, entity type, proportionality tier, and starting pillars.
Behavior: This tool is read-only and stateless — 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: description (str): The 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 — 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: description (required), api_key. Returns: result
classify_incidentA
Classify an ICT incident against DORA major-incident thresholds per Commission Delegated Regulation (EU) 2024/1772. Returns whether it qualifies as a 'major ICT incident' requiring 4h/72h/1-month reporting.
Behavior: This tool is read-only and stateless — 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: incident_description (str): The incident description to analyze or process. clients_affected (int): The clients affected to analyze or process. duration_hours (float): The duration hours to analyze or process. economic_impact_eur (float): The economic impact eur to analyze or process. data_loss (bool): The data loss 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 — 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: incident_description (required), clients_affected, duration_hours, economic_impact_eur, +2 more. Returns: result
enforcement_statusA
Current DORA enforcement status + key upcoming deadlines for financial entities.
Behavior: This tool is read-only and stateless — 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 — 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
get_dora_certificateA
Generate a cryptographically signed DORA compliance attestation (Pro/Enterprise).
Uses the shared MEOK attestation module (HMAC-SHA256 signed JSON + verify URL + optional base64-encoded PDF). Share the verify_url with your auditor / board / procurement team — the signature is cryptographically binding and any tampering invalidates it. Certificates expire 365 days from issue.
Args: entity_name (str): The entity name to appear on the certificate. overall_score (float): Overall compliance score (0–100). findings_csv (str): Comma-separated list of article-level findings (e.g. "Article 9: PASS,Article 28: GAP") articles_audited_csv (str): Comma-separated article numbers (e.g. "9,10,28") include_pdf_base64 (bool): Set True to also receive a board-ready PDF as base64. api_key (str): MEOK API key (Pro/Enterprise tier).
Inputs: entity_name (required), overall_score (required), findings_csv, articles_audited_csv, +2 more. Returns: result
list_pillarsA
List all 5 DORA pillars with article ranges and key obligations.
Behavior: This tool is read-only and stateless — 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 — 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
register_of_information_templateA
Return the Article 28.3 Register of Information template structure. Financial entities must submit this annually to their competent authority under DORA.
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: 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 — 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
tlpt_readinessA
Assess Threat-Led Penetration Testing (Article 26) readiness. Returns whether the entity is likely in scope and what's needed to pass a TIBER-EU-aligned TLPT.
Behavior: This tool is read-only and stateless — 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: entity_description (str): The entity 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 — 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: entity_description (required), api_key. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: auditing all or specific pillars, classifying entities or incidents, checking enforcement status, generating certificates, listing pillars, providing template, and TLPT readiness. No two tools overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., audit_pillar, classify_incident, list_pillars). Naming is predictable and immediately conveys the action and target.
9 tools is well-scoped for a DORA compliance server. Each tool earns its place, covering auditing, classification, status, certificate, and documentation needs without bloat or deficiency.
The tool set covers the core DORA compliance workflow: entity classification, pillar audits, incident classification, enforcement status, certificate generation, and templates. Minor gaps exist (e.g., no tool for tracking remediation or generating full reports), but the surface is largely complete for assessment and documentation.
Maintenance
Related MCP Connectors
AI governance MCP server for EU AI Act compliance and jurisdiction verification
DORA OS Conductor — 16-tool meta-orchestrator for DORA compliance workflow automation.
BC/DR & compliance tools: DORA, NIS2, NIST CSF, GDPR, SOC 2, CMMC, CAF, ISO 27001, FCA/PRA.
Compliance frameworks (SOC 2, ISO 27001, CMMC, NIST, more) delivered to AI agents as MCP tools.
Related MCP Servers
- AlicenseAqualityCmaintenanceCSRD Compliance - MCP server providing AI-powered tools and automation by MEOK AI Labs652 PyPIMIT
- AlicenseAqualityCmaintenanceEU AI Act Compliance - MCP server providing AI-powered tools and automation by MEOK AI Labs111MIT

SOC2 Compliance AI MCPofficial
AlicenseAqualityCmaintenanceSOC2 Compliance AI - MCP server providing AI-powered tools and automation by MEOK AI Labs66 npm70 PyPIMIT- AlicenseAqualityCmaintenanceNIS2 Compliance - MCP server providing AI-powered tools and automation by MEOK AI Labs753 PyPIMIT