generated: '2026-07-19'
method: searched
source:
- openapi/heymilo-openapi-original.json
- https://trust.warden-ai.com/heymilo
- https://docs.heymilo.ai
standards:
- id: openapi-3.1
  conforms: true
  evidence: openapi/heymilo-openapi-original.json declares openapi 3.1.0
- id: oauth2.1
  conforms: true
  evidence: MCP server publishes RFC 8414 metadata; authorization_code + PKCE S256, refresh_token
- id: rfc8414-oauth-as-metadata
  conforms: true
  evidence: https://mcp.heymilo.ai/.well-known/oauth-authorization-server returns 200
- id: rfc9728-protected-resource-metadata
  conforms: true
  evidence: https://mcp.heymilo.ai/.well-known/oauth-protected-resource returns 200
- id: mcp
  conforms: true
  evidence: hosted Model Context Protocol server at https://mcp.heymilo.ai/mcp
- id: rfc9457-problem-details
  conforms: false
  evidence: errors use a custom { error } envelope, not application/problem+json
- id: cursor-pagination
  conforms: true
  evidence: list endpoints paginate with starting_after + limit
- id: idempotency
  conforms: false
  evidence: no idempotency-key mechanism documented
compliance_programs:
- name: Warden AI — AI Assurance / continuous bias auditing
  url: https://trust.warden-ai.com/heymilo
  audit_frequency: monthly
  latest_audit: '2026-07-09'
  sample_size: 17442
  regulations:
  - New York City Local Law 144
  - EU AI Act (Regulation 2024/1689)
  - Colorado SB 26-189
  - California FEHA
  result: all bias/fairness categories Clear
  notes: >-
    Third-party independent AI assurance covering sex, race/ethnicity,
    intersectional, age, disability, religion, sexual orientation, veteran status,
    English proficiency, pregnancy, national origin, criminal history, medical
    condition, gender identity, and marital status bias. Post-market monitoring
    with transparent public reporting.