neural_insights

Instructions

Implementation Reference

• server.py:1911-1949 (handler)

  The neural_insights tool handler function. Decorated with @mcp.tool(), it checks access/rate limits, verifies the neural engine is available, and delegates to _neural_net.get_insights() to return aggregate learning insights from the neural compliance model.

  def neural_insights(api_key: str = "") -> dict:
      """Get aggregate learning insights from the neural compliance model — training history, maturity, and common risk patterns.
  
      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.
      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.
      """
      allowed, msg, tier = check_access(api_key)
      if not allowed:
          return {"error": msg, "upgrade_url": "https://meok.ai/pricing"}
      if _neural_net is None:
          return {"error": "Neural engine not available. Install meok-labs-engine for neural insights."}
      return _neural_net.get_insights()

• server.py:1910-1911 (registration)

  Registration of neural_insights as an MCP tool via the @mcp.tool() decorator on the FastMCP 'mcp' server instance (line 429).

  @mcp.tool()
  def neural_insights(api_key: str = "") -> dict:

• server.py:1911-1943 (schema)

  Input schema: accepts an optional 'api_key' string parameter. Return type is dict.

  def neural_insights(api_key: str = "") -> dict:
      """Get aggregate learning insights from the neural compliance model — training history, maturity, and common risk patterns.
  
      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.
      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.
      """

• server.py:33-34 (helper)

  The _neural_net helper object (ComplianceNeuralNet) that neural_insights delegates to via _neural_net.get_insights(). Imported from shared module compliance_neural.

  from compliance_neural import ComplianceNeuralNet
  _neural_net = ComplianceNeuralNet("eu-ai-act")

• server.py:36-37 (helper)

  Fallback when neural engine is not available: _neural_net remains None, causing neural_insights to return an error message.

  except ImportError:
      _AUTH_ENGINE_AVAILABLE = False