generated: '2026-08-06'
method: derived
status: candidate
source: openapi/activefence-alice-api-openapi.yml
published_server: null
published_server_note: 'NO official hosted or remote MCP server was found for ActiveFence/Alice. This
  file is a DERIVED CANDIDATE tool surface computed from the provider''s OpenAPI so an integrator can
  stand one up. It is deliberately NOT wired as a `type: MCPServer` pointer in apis.yml — the provider
  does not publish an MCP server and must not be credited with one.'
probes:
- url: https://mcp.alice.io/
  result: NXDOMAIN
- url: https://api.alice.io/mcp
  http_status: 404
- url: https://alice.io/.well-known/mcp.json
  http_status: 404
- source: https://api.github.com/orgs/ActiveFence/repos
  http_status: 200
  finding: 3 public repos — OTLP-GitHubAction-Exporter, parlant-alice, bull. No MCP server.
- source: https://api.github.com/orgs/alice-dot-io/repos
  http_status: 200
  finding: 1 public repo — caterpillar. No MCP server.
- source: https://alice.io/llms.txt
  http_status: 200
  finding: lists integrations for Bedrock/AgentCore, Strands, LangGraph, Copilot Studio, Databricks, NeMo
    Guardrails and Parlant — none of them an MCP server.
- source: npm registry search @alice-io
  result: 2 packages, neither an MCP server
transport_if_built: http
auth_if_built:
  scheme: apiKey
  header: af-api-key
  note: inherits the REST contract; there is no OAuth surface to negotiate
tools:
- name: moderate_text
  description: Analyze a text item for policy violations and return risk scores. Blocks until analysis
    completes.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-sync-content-text
- name: moderate_text_bulk
  description: Analyze a batch of text items in one synchronous call.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-sync-content-bulk-text
- name: moderate_image
  description: Analyze an image for policy violations and return risk scores. Blocks until analysis completes.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-sync-content-image
- name: submit_text_for_analysis
  description: Submit text for asynchronous analysis; result is posted to a callback URL.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-content-text
- name: submit_image_for_analysis
  description: Submit an image for asynchronous analysis.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-content-image
- name: submit_video_for_analysis
  description: Submit a video for asynchronous analysis.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-content-video
- name: submit_audio_for_analysis
  description: Submit audio for asynchronous analysis.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-content-audio
- name: upsert_users
  description: Create or update end-user records on the moderation platform.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-users-upsert
- name: upsert_collection
  description: Create or update a collection (playlist, album, folder, group, channel).
  source_operation: openapi/activefence-alice-api-openapi.yml#post-collections
- name: report_flag
  description: Send a user-raised flag against a content item, collection or user.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-flags
- name: evaluate_genai_message
  description: Evaluate a GenAI prompt or response against WonderFence runtime guardrails.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-genai-evaluate
- name: list_assessments
  description: List WonderBuild red-team assessments with filters and pagination.
  source_operation: openapi/activefence-alice-api-openapi.yml#get-assessments
- name: run_assessment
  description: Run an existing WonderBuild red-team assessment by id.
  source_operation: openapi/activefence-alice-api-openapi.yml#run-assessment
- name: clone_and_run_assessment
  description: Clone an existing assessment and run the copy.
  source_operation: openapi/activefence-alice-api-openapi.yml#clone-and-run-assessment
- name: run_assessment_from_preset
  description: Run a red-team assessment from a preset configuration.
  source_operation: openapi/activefence-alice-api-openapi.yml#run-assessment-preset
- name: create_api_key
  description: Generate a new Alice API key.
  source_operation: openapi/activefence-alice-api-openapi.yml#post-generate-api-key
- name: list_api_keys
  description: List existing Alice API keys.
  source_operation: openapi/activefence-alice-api-openapi.yml#get-api-keys
- name: delete_api_key
  description: Delete an Alice API key by id.
  source_operation: openapi/activefence-alice-api-openapi.yml#delete-api-key
excluded_from_candidate_surface:
  note: The three api-key tools are included for completeness but SHOULD NOT be exposed to an autonomous
    agent — see agentic-access/activefence-agentic-access.yml, where key management is the operation class
    that carries the highest consequence in this API.
coverage:
  rest_operations_total: 18
  tools_derived: 18
  tools_published_by_provider: 0
deployment:
  mode: none
  verified: derived
  tools: 18
  checked: '2026-08-12'
  source: catalog MCP census