vocabulary: "1.0.0"

info:
  provider: "Airbyte"
  description: "Unified taxonomy of the Airbyte data integration platform, covering the operational API surface (sources, destinations, connections, jobs) and capability workflows for data engineering personas."
  created: "2026-04-19"
  modified: "2026-04-19"

operational:
  apis:
    - name: Airbyte Public API
      namespace: airbyte
      version: "1.0.0"
      baseUrl: https://api.airbyte.com/v1
      status: active
      description: "Programmatic control over Airbyte Cloud, OSS & Enterprise."

  resources:
    - name: sources
      api: airbyte
      description: "Data source connectors (databases, SaaS APIs, files)."
      actions: [list, create, get, update, delete]
    - name: destinations
      api: airbyte
      description: "Data destination connectors (warehouses, lakes, databases)."
      actions: [list, create, get, update, delete]
    - name: connections
      api: airbyte
      description: "Links between sources and destinations with sync configuration."
      actions: [list, create, get, update, delete]
    - name: jobs
      api: airbyte
      description: "Sync job executions for connections."
      actions: [list, create, get, cancel]
    - name: workspaces
      api: airbyte
      description: "Organizational units for grouping resources."
      actions: [list, create, get, update, delete]
    - name: organizations
      api: airbyte
      description: "Top-level organizational accounts."
      actions: [list, get, update]
    - name: users
      api: airbyte
      description: "User accounts within an organization."
      actions: [list, get, create, delete]
    - name: permissions
      api: airbyte
      description: "Access control permissions for resources."
      actions: [list, create, get, delete]
    - name: connector-definitions
      api: airbyte
      description: "Available connector types for sources and destinations."
      actions: [list, get]
    - name: applications
      api: airbyte
      description: "API applications for programmatic access."
      actions: [list, create, get, delete]
    - name: streams
      api: airbyte
      description: "Individual data streams within a source connection."
      actions: [list, get]

  actions:
    - name: list
      methods: [GET]
      pattern: read
      description: "Retrieve a paginated collection of resources."
    - name: get
      methods: [GET]
      pattern: read
      description: "Retrieve a single resource by ID."
    - name: create
      methods: [POST]
      pattern: write
      description: "Create a new resource."
    - name: update
      methods: [PUT, PATCH]
      pattern: write
      description: "Update an existing resource."
    - name: delete
      methods: [DELETE]
      pattern: destructive
      description: "Delete a resource by ID."
    - name: trigger
      methods: [POST]
      pattern: write
      description: "Trigger an async operation (sync job)."
    - name: cancel
      methods: [DELETE, POST]
      pattern: write
      description: "Cancel an in-progress operation."

  schemas:
    core:
      - name: SourceResponse
        description: "Source connector configuration and status."
      - name: DestinationResponse
        description: "Destination connector configuration and status."
      - name: ConnectionResponse
        description: "Connection configuration between source and destination."
      - name: JobResponse
        description: "Sync job execution details and status."
      - name: WorkspaceResponse
        description: "Workspace configuration."
    admin:
      - name: UserResponse
        description: "User account details."
      - name: PermissionResponse
        description: "Access control permission details."
      - name: OrganizationResponse
        description: "Organization account details."

  parameters:
    pagination:
      - name: limit
        type: integer
        description: "Number of results per page."
      - name: offset
        type: integer
        description: "Offset for pagination."
    identifiers:
      - name: sourceId
        type: string
        description: "Unique identifier for a source."
      - name: destinationId
        type: string
        description: "Unique identifier for a destination."
      - name: connectionId
        type: string
        description: "Unique identifier for a connection."
      - name: jobId
        type: integer
        description: "Unique identifier for a job."
      - name: workspaceId
        type: string
        description: "Unique identifier for a workspace."
    filters:
      - name: status
        type: string
        description: "Filter by status (running, succeeded, failed, cancelled)."
      - name: workspaceId
        type: string
        description: "Filter resources by workspace."

  enums:
    job_status:
      - pending
      - running
      - incomplete
      - failed
      - succeeded
      - cancelled
    connection_status:
      - active
      - inactive
      - deprecated
    schedule_type:
      - manual
      - basic
      - cron

  authentication:
    schemes:
      - type: bearer
        description: "Short-lived access token obtained via Airbyte UI Settings > Applications."
        apis: [airbyte]

capability:
  workflows:
    - name: Data Pipeline Management
      file: capabilities/data-pipeline-management.yaml
      description: "Manage Airbyte sources, destinations, connections, and sync jobs."
      apis: [airbyte]
      tools: 11
      personas: [Data Engineer, Platform Admin]
      domains: [Data Integration, Pipeline Operations]

  personas:
    - id: data-engineer
      name: Data Engineer
      description: "Builds and maintains data pipelines using Airbyte connectors and connections."
      workflows: [Data Pipeline Management]
    - id: platform-admin
      name: Platform Admin
      description: "Manages Airbyte workspaces, users, permissions, and organizational settings."
      workflows: [Data Pipeline Management]

  domains:
    - name: Data Integration
      description: "Moving data between sources and destinations."
      resources: [sources, destinations, connections]
    - name: Pipeline Operations
      description: "Monitoring and operating sync pipelines."
      resources: [jobs, streams]
    - name: Administration
      description: "User, workspace, and organizational management."
      resources: [workspaces, organizations, users, permissions]

  namespaces:
    - name: airbyte
      type: consumed
      baseUri: https://api.airbyte.com/v1
    - name: airbyte-pipeline-api
      type: rest
      port: 8080
    - name: airbyte-pipeline-mcp
      type: mcp
      port: 9090

  binds:
    - name: AIRBYTE_API_TOKEN
      description: "Bearer token for authenticating with the Airbyte API."
      workflows: [Data Pipeline Management]

crossReference:
  - resource: sources
    operations: [listSources, createSource, getSource, updateSource, deleteSource]
    workflows: [Data Pipeline Management]
    personas: [Data Engineer]
  - resource: destinations
    operations: [listDestinations, createDestination, getDestination, updateDestination, deleteDestination]
    workflows: [Data Pipeline Management]
    personas: [Data Engineer]
  - resource: connections
    operations: [listConnections, createConnection, getConnection, updateConnection, deleteConnection]
    workflows: [Data Pipeline Management]
    personas: [Data Engineer]
  - resource: jobs
    operations: [listJobs, createJob, getJob, cancelJob]
    workflows: [Data Pipeline Management]
    personas: [Data Engineer, Platform Admin]
  - resource: workspaces
    operations: [listWorkspaces, createWorkspace, getWorkspace, updateWorkspace, deleteWorkspace]
    workflows: [Data Pipeline Management]
    personas: [Platform Admin]