Amazon Forecast Agentic Access
Amazon Forecast exposes 64 API operations that an AI agent could call, of which 49 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: 15 read, 48 write, and 1 safety-critical.
1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.
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.
API Evangelist recommendations, not provider rules. These classifications are generated heuristically from each operation's method, path and name. They suggest how an agent's access could be scoped. They are not authorization, approval or human-in-the-loop requirements that the provider enforces.
By consequence
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 | Recommended human-in-loop |
|---|---|---|---|
| POST | /#StopResource | safety-critical | required |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/amazon-forecast-dataset-groups-api-openapi.yml, openapi/amazon-forecast-dataset-import-job-api-openapi.yml,
openapi/amazon-forecast-datasets-api-openapi.yml, openapi/amazon-forecast-explainability-api-openapi.yml,
openapi/amazon-forecast-explainability-export-api-openapi.yml, openapi/amazon-forecast-export-jobs-api-openapi.yml,
openapi/amazon-forecast-forecast-export-job-api-openapi.yml, openapi/amazon-forecast-forecasts-api-openapi.yml,
openapi/amazon-forecast-monitor-api-openapi.yml, openapi/amazon-forecast-operations-api-openapi.yml,
openapi/amazon-forecast-predictor-backtest-export-job-api-openapi.yml, openapi/amazon-forecast-predictors-api-openapi.yml,
openapi/amazon-forecast-resource-api-openapi.yml, openapi/amazon-forecast-tags-api-openapi.yml,
openapi/amazon-forecast-what-if-analysis-api-openapi.yml, openapi/amazon-forecast-what-if-forecast-api-openapi.yml,
openapi/amazon-forecast-what-if-forecast-export-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: 64
by_action_class:
acting: 49
connected: 15
by_consequence:
write: 48
read: 15
safety-critical: 1
human_in_the_loop_required: 1
operations:
- path: /#CreateDatasetGroup
method: post
operationId: CreateDatasetGroup
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteDatasetGroup
method: post
operationId: DeleteDatasetGroup
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeDatasetGroup
method: post
operationId: DescribeDatasetGroup
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListDatasetGroups
method: post
operationId: ListDatasetGroups
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#UpdateDatasetGroup
method: post
operationId: UpdateDatasetGroup
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#CreateDatasetImportJob
method: post
operationId: CreateDatasetImportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteDatasetImportJob
method: post
operationId: DeleteDatasetImportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeDatasetImportJob
method: post
operationId: DescribeDatasetImportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListDatasetImportJobs
method: post
operationId: ListDatasetImportJobs
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#CreateDataset
method: post
operationId: CreateDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteDataset
method: post
operationId: DeleteDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeDataset
method: post
operationId: DescribeDataset
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListDatasets
method: post
operationId: ListDatasets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateExplainability
method: post
operationId: CreateExplainability
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteExplainability
method: post
operationId: DeleteExplainability
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeExplainability
method: post
operationId: DescribeExplainability
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListExplainabilities
method: post
operationId: ListExplainabilities
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateExplainabilityExport
method: post
operationId: CreateExplainabilityExport
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteExplainabilityExport
method: post
operationId: DeleteExplainabilityExport
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeExplainabilityExport
method: post
operationId: DescribeExplainabilityExport
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListExplainabilityExports
method: post
operationId: ListExplainabilityExports
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateForecastExportJob
method: post
operationId: CreateForecastExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#CreateForecastExportJob
method: post
operationId: CreateForecastExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteForecastExportJob
method: post
operationId: DeleteForecastExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeForecastExportJob
method: post
operationId: DescribeForecastExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListForecastExportJobs
method: post
operationId: ListForecastExportJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateForecast
method: post
operationId: CreateForecast
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteForecast
method: post
operationId: DeleteForecast
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeForecast
method: post
operationId: DescribeForecast
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListForecasts
method: post
operationId: ListForecasts
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateMonitor
method: post
operationId: CreateMonitor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteMonitor
method: post
operationId: DeleteMonitor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeMonitor
method: post
operationId: DescribeMonitor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListMonitors
method: post
operationId: ListMonitors
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ResumeResource
method: post
operationId: ResumeResource
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#CreateAutoPredictor
method: post
operationId: CreateAutoPredictor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeAutoPredictor
method: post
operationId: DescribeAutoPredictor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteResourceTree
method: post
operationId: DeleteResourceTree
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#GetAccuracyMetrics
method: post
operationId: GetAccuracyMetrics
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListMonitorEvaluations
method: post
operationId: ListMonitorEvaluations
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListWhatIfAnalyses
method: post
operationId: ListWhatIfAnalyses
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreatePredictorBacktestExportJob
method: post
operationId: CreatePredictorBacktestExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeletePredictorBacktestExportJob
method: post
operationId: DeletePredictorBacktestExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribePredictorBacktestExportJob
method: post
operationId: DescribePredictorBacktestExportJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListPredictorBacktestExportJobs
method: post
operationId: ListPredictorBacktestExportJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreatePredictor
method: post
operationId: CreatePredictor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeletePredictor
method: post
operationId: DeletePredictor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribePredictor
method: post
operationId: DescribePredictor
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListPredictors
method: post
operationId: ListPredictors
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#StopResource
method: post
operationId: StopResource
x-agentic-access:
action-class: acting
consequence: safety-critical
subject: required
audience: null
token:
max-ttl: 120
exchange: true
purpose-required: true
proof-of-possession: true
escalation:
human-in-the-loop: required
audit: required
- path: /#TagResource
method: post
operationId: TagResource
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#UntagResource
method: post
operationId: UntagResource
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListTagsForResource
method: post
operationId: ListTagsForResource
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateWhatIfAnalysis
method: post
operationId: CreateWhatIfAnalysis
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteWhatIfAnalysis
method: post
operationId: DeleteWhatIfAnalysis
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeWhatIfAnalysis
method: post
operationId: DescribeWhatIfAnalysis
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#CreateWhatIfForecast
method: post
operationId: CreateWhatIfForecast
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteWhatIfForecast
method: post
operationId: DeleteWhatIfForecast
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeWhatIfForecast
method: post
operationId: DescribeWhatIfForecast
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListWhatIfForecasts
method: post
operationId: ListWhatIfForecasts
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateWhatIfForecastExport
method: post
operationId: CreateWhatIfForecastExport
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DeleteWhatIfForecastExport
method: post
operationId: DeleteWhatIfForecastExport
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#DescribeWhatIfForecastExport
method: post
operationId: DescribeWhatIfForecastExport
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /#ListWhatIfForecastExports
method: post
operationId: ListWhatIfForecastExports
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
Work with this as data
Every access contract here is available over the APIs.io API and to AI agents over MCP. Agentic Access is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for agentic access
3 MCP tools reach this
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/search?q=amazon-forecast-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/amazon-forecast-agentic-access"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.