generate_documentation

Instructions

Implementation Reference

• server.py:1005-1273 (handler)

  The main handler function for the 'generate_documentation' MCP tool. Decorated with @mcp.tool(), it accepts system details as inputs and generates a complete Annex IV-compliant technical documentation template in markdown format, following the 8-section structure required by Article 11 of the EU AI Act.

  @mcp.tool()
  def generate_documentation(
      system_name: str,
      provider_name: str,
      provider_contact: str,
      version: str,
      intended_purpose: str,
      description: str,
      data_description: str,
      architecture_description: str,
      performance_metrics: str = "",
      risk_management_description: str = "",
      human_oversight_description: str = "",
      caller: str = "anonymous",
      api_key: str = "") -> str:
      """Generate Article 11 / Annex IV compliant technical documentation template.
  
      Produces a complete markdown template following the Annex IV structure of the
      EU AI Act. Fill in the bracketed sections with your specific information.
  
      Args:
          system_name: Name of the AI system.
          provider_name: Legal name of the AI system provider.
          provider_contact: Provider contact details (address, email, phone).
          version: System version number/identifier.
          intended_purpose: Clear description of the system's intended purpose.
          description: General description of what the system does.
          data_description: Description of training/validation/testing data used.
          architecture_description: Description of system architecture and algorithms.
          performance_metrics: Known accuracy/performance metrics (if available).
          risk_management_description: Description of risk management measures (if available).
          human_oversight_description: Description of human oversight measures (if available).
          caller: Identifier for rate limiting.
          tier: "free" (10 calls/day) or "pro" (unlimited, $29/mo).
  
      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.
      """
      allowed, msg, tier = check_access(api_key)
      if not allowed:
          return {"error": msg, "upgrade_url": "https://meok.ai/pricing"}
      limit_err = _check_rate_limit(caller, tier)
      if limit_err:
          return {"error": "rate_limited", "message": limit_err}
  
      date_str = datetime.now().strftime("%Y-%m-%d")
  
      doc = f"""# Technical Documentation — EU AI Act Annex IV
  ## {system_name}
  
  **Provider:** {provider_name}
  **Contact:** {provider_contact}
  **Version:** {version}
  **Document Date:** {date_str}
  **Regulation:** Regulation (EU) 2024/1689 — Article 11, Annex IV
  **Generated by:** MEOK AI Labs EU AI Act Compliance Server (https://meok.ai)
  
  ---
  
  ## 1. General Description of the AI System (Annex IV, Section 1)
  
  ### 1.1 Intended Purpose
  {intended_purpose}
  
  ### 1.2 Provider Information
  - **Provider Name:** {provider_name}
  - **Contact Details:** {provider_contact}
  - **System Version:** {version}
  - **Date of this version:** {date_str}
  - **Previous versions:** [List previous versions and dates]
  
  ### 1.3 System Description
  {description}
  
  ### 1.4 Interaction with External Hardware/Software
  [Describe how the AI system interacts with hardware or software that is not part of the AI system itself, including APIs, data feeds, external services]
  
  ### 1.5 Software/Firmware Requirements
  [List relevant software and firmware versions, plus any version update requirements]
  
  ### 1.6 Forms of Market Placement
  [Describe all forms in which the system is placed on the market or put into service: SaaS, on-premise, embedded, API, etc.]
  
  ### 1.7 Hardware Requirements
  [Describe the hardware on which the AI system is intended to run, including computational requirements]
  
  ### 1.8 User Interface
  [Describe the user interface provided to the deployer, including screenshots or diagrams]
  
  ---
  
  ## 2. Detailed Description of Elements and Development Process (Annex IV, Section 2)
  
  ### 2.1 Development Methods and Steps
  [Describe the methods and steps performed for the development of the AI system, including any use of pre-trained systems or third-party tools/components]
  
  ### 2.2 Design Specifications
  
  #### 2.2.1 General Logic and Algorithms
  {architecture_description}
  
  #### 2.2.2 Key Design Choices and Rationale
  [Document key design choices including algorithmic approach, model architecture, training methodology, and the rationale for each decision]
  
  #### 2.2.3 Classification and Optimisation Approach
  [Describe what the system is designed to optimise for, the relevance of different parameters, and classification methodology]
  
  #### 2.2.4 Expected Output and Interpretation
  [Describe the expected output of the system and how it should be interpreted]
  
  ### 2.3 System Architecture
  [Provide detailed system architecture diagram and explanation of how software components build on or feed into each other]
  
  ### 2.4 Computational Resources
  [Document all computational resources used in development, training, and deployment — including hardware specifications, cloud services, GPU/TPU usage]
  
  ### 2.5 Data Requirements and Documentation
  
  #### 2.5.1 Data Description
  {data_description}
  
  #### 2.5.2 Data Collection Methodology
  [Describe how data was collected, including sources, timeframes, and sampling approaches]
  
  #### 2.5.3 Data Characteristics
  [Document scope, size, format, and key statistical properties of datasets]
  
  #### 2.5.4 Bias Assessment
  [Document assessment of biases in training data and mitigation measures applied]
  
  ### 2.6 Human Oversight Assessment (per Article 14)
  {human_oversight_description if human_oversight_description else "[Describe the human oversight measures needed, as assessed under Article 14. Include how humans can intervene, override, or stop the system.]"}
  
  ### 2.7 Pre-determined Changes
  [Document any pre-determined changes to the system and its performance that have been assessed at the time of the initial conformity assessment]
  
  ---
  
  ## 3. Monitoring, Functioning, and Control (Annex IV, Section 3)
  
  ### 3.1 Capabilities and Limitations
  {performance_metrics if performance_metrics else "[Document the capabilities and limitations of the AI system, including degrees and range of accuracy for specific groups/contexts]"}
  
  ### 3.2 Foreseeable Unintended Outcomes and Risk Sources
  [Identify reasonably foreseeable unintended outcomes and sources of risk to health, safety, and fundamental rights]
  
  ### 3.3 Human Oversight Measures
  {human_oversight_description if human_oversight_description else "[Detail the specific human oversight measures built into or alongside the system]"}
  
  ### 3.4 Input Data Specifications
  [Specify the input data requirements and expected data formats]
  
  ### 3.5 Output Interpretation Guidance
  [Provide information enabling deployers to correctly interpret the AI system's output]
  
  ---
  
  ## 4. Appropriateness of Performance Metrics (Annex IV, Section 4)
  
  ### 4.1 Metrics Used
  {performance_metrics if performance_metrics else "[List all metrics used to measure accuracy, robustness, and compliance with other requirements set out in Article 15]"}
  
  ### 4.2 Testing and Validation Methodology
  [Describe the testing and validation approaches and methodologies used, including information about the test data used and its main characteristics, metrics used to measure accuracy/robustness and any other relevant requirement]
  
  ### 4.3 Performance Declarations
  [Document the expected level of performance and any declarations of conformity]
  
  ---
  
  ## 5. Risk Management System — Article 9 (Annex IV, Section 5)
  
  ### 5.1 Risk Management System Description
  {risk_management_description if risk_management_description else "[Describe the risk management system as required by Article 9, including: identification of known and foreseeable risks, estimation of risks from intended use and foreseeable misuse, evaluation of risks, adoption of mitigation measures]"}
  
  ### 5.2 Development and Post-Development Risk Minimisation
  [Document choices made during and after development to minimise risk, including testing procedures and results]
  
  ---
  
  ## 6. Changes Throughout the Lifecycle (Annex IV, Section 6)
  
  ### 6.1 Pre-determined Changes
  [Document all pre-determined changes to the system throughout its lifecycle]
  
  ### 6.2 Data Governance and Management Practices (Article 10)
  [Describe data governance and management practices, including data collection, data origin, and data scope]
  
  ---
  
  ## 7. EU Declaration of Conformity — Article 47 (Annex IV, Section 7)
  
  [Reference to the EU declaration of conformity as required by Article 47. This section should be completed after conformity assessment.]
  
  - **Conformity Assessment Body (if applicable):** [Name and notified body number]
  - **Conformity Assessment Procedure:** [Self-assessment per Article 43(1) / Third-party assessment per Article 43(2)]
  - **Declaration Reference Number:** [To be assigned]
  
  ---
  
  ## 8. Post-Market Monitoring System — Article 72 (Annex IV, Section 8)
  
  [Describe the post-market monitoring system established pursuant to Article 72, including: monitoring methodology, data collection from deployers, incident reporting procedures, periodic review schedule]
  
  ---
  
  ## Document Control
  
  | Field | Value |
  |-------|-------|
  | Document Owner | {provider_name} |
  | Classification | [Internal/Confidential/Public] |
  | Review Cycle | [Annually/Upon significant change] |
  | Next Review | [Date] |
  | Approval Authority | [Name and role] |
  
  ---
  
  *This template was generated by the MEOK AI Labs EU AI Act Compliance MCP Server.
  It follows the structure required by Annex IV of Regulation (EU) 2024/1689.
  All bracketed sections must be completed with system-specific information.
  This template does not constitute legal advice — consult qualified legal counsel.*
  
  *MEOK AI Labs | https://meok.ai*
  """
  
      return {
          "document_format": "markdown",
          "template": doc,
          "sections_requiring_completion": [
              "1.4 Interaction with External Hardware/Software",
              "1.5 Software/Firmware Requirements",
              "1.6 Forms of Market Placement",
              "1.7 Hardware Requirements",
              "1.8 User Interface",
              "2.1 Development Methods and Steps",
              "2.2.2 Key Design Choices and Rationale",
              "2.2.3 Classification and Optimisation Approach",
              "2.2.4 Expected Output and Interpretation",
              "2.3 System Architecture",
              "2.4 Computational Resources",
              "2.5.2 Data Collection Methodology",
              "2.5.3 Data Characteristics",
              "2.5.4 Bias Assessment",
              "2.7 Pre-determined Changes",
              "3.2 Foreseeable Unintended Outcomes",
              "3.4 Input Data Specifications",
              "4.2 Testing and Validation Methodology",
              "4.3 Performance Declarations",
              "6.1 Pre-determined Changes",
              "6.2 Data Governance",
              "7. EU Declaration of Conformity",
              "8. Post-Market Monitoring System",
          ],
          "compliance_note": "Complete all bracketed sections before submission. Article 11(1) requires documentation to be drawn up before the system is placed on the market.",
          "meok_labs": "https://meok.ai",
      }

• server.py:1005-1005 (registration)

  The tool is registered via the @mcp.tool() decorator on the generate_documentation function in the FastMCP server instance 'mcp'.

  @mcp.tool()

• server.py:1006-1019 (schema)

  The function signature defines the input schema: system_name, provider_name, provider_contact, version, intended_purpose, description, data_description, architecture_description are required strings; performance_metrics, risk_management_description, human_oversight_description, caller, api_key are optional strings with defaults.

  def generate_documentation(
      system_name: str,
      provider_name: str,
      provider_contact: str,
      version: str,
      intended_purpose: str,
      description: str,
      data_description: str,
      architecture_description: str,
      performance_metrics: str = "",
      risk_management_description: str = "",
      human_oversight_description: str = "",
      caller: str = "anonymous",
      api_key: str = "") -> str:

• server.py:48-51 (helper)

  Helper function called by generate_documentation for authentication/access control before generating documentation.

  def check_access(api_key: str = ""):
      """Unified access check — works with or without shared auth engine."""
      return _shared_check_access(api_key)