Mindee · Agentic Access

Mindee Agentic Access

x-agentic-access generated

Mindee exposes 13 API operations that an AI agent could call, of which 6 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 7 read and 6 physical.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

Document ParsingOCRIDPAIMachine LearningInvoicesReceiptsIDsComputer Vision

Operations: 13 Acting: 6 Human-in-the-loop: 0 Method: generated

By consequence

read 7 physical 6

Highest-consequence actions

The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.

Method	Path	Consequence	Human-in-loop
POST	/v2/inferences/enqueue	physical	conditional
POST	/v2/products/classification/enqueue	physical	conditional
POST	/v2/products/crop/enqueue	physical	conditional
POST	/v2/products/extraction/enqueue	physical	conditional
POST	/v2/products/ocr/enqueue	physical	conditional
POST	/v2/products/split/enqueue	physical	conditional

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/mindee-classification-api-openapi.yml, openapi/mindee-crop-api-openapi.yml,
  openapi/mindee-extraction-api-openapi.yml, openapi/mindee-jobs-api-openapi.yml, openapi/mindee-ocr-api-openapi.yml,
  openapi/mindee-split-api-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 13
  by_action_class:
    acting: 6
    connected: 7
  by_consequence:
    physical: 6
    read: 7
  human_in_the_loop_required: 0
operations:
- path: /v2/products/classification/enqueue
  method: post
  operationId: Enqueue_Classification_Product_Inference_v2_products_classification_enqueue_post
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/products/classification/results/{inference_id}
  method: get
  operationId: Get_classification_Product_Result_v2_products_classification_results__inference_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/products/crop/enqueue
  method: post
  operationId: Enqueue_Crop_Product_Inference_v2_products_crop_enqueue_post
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/products/crop/results/{inference_id}
  method: get
  operationId: Get_Crop_Product_Result_v2_products_crop_results__inference_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/products/extraction/enqueue
  method: post
  operationId: Enqueue_Extraction_Product_Inference_v2_products_extraction_enqueue_post
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/inferences/enqueue
  method: post
  operationId: Enqueue_Extraction_Product_Inference_v2_inferences_enqueue_post
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/products/extraction/results/{inference_id}
  method: get
  operationId: Get_Extraction_Product_Result_v2_products_extraction_results__inference_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/inferences/{inference_id}
  method: get
  operationId: Get_Extraction_Product_Result_v2_inferences__inference_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/jobs/{job_id}
  method: get
  operationId: Get_Job_Status_v2_jobs__job_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/products/ocr/enqueue
  method: post
  operationId: Enqueue_OCR_Product_Inference_v2_products_ocr_enqueue_post
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/products/ocr/results/{inference_id}
  method: get
  operationId: Get_OCR_Product_Result_v2_products_ocr_results__inference_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /v2/products/split/enqueue
  method: post
  operationId: Enqueue_Split_Product_Inference_v2_products_split_enqueue_post
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /v2/products/split/results/{inference_id}
  method: get
  operationId: Get_Split_Product_Result_v2_products_split_results__inference_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none