Amazon EMR Agentic Access
Amazon EMR exposes 65 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: 16 read, 46 write, and 3 safety-critical.
3 operations 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 | /#StopNotebookExecution | safety-critical | required |
| POST | /#TerminateJobFlows | safety-critical | required |
| POST | /#TerminateSession | safety-critical | required |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/amazon-emr-auto-termination-policy-api-openapi.yml, openapi/amazon-emr-clusters-api-openapi.yml,
openapi/amazon-emr-instance-fleet-api-openapi.yml, openapi/amazon-emr-instance-group-api-openapi.yml,
openapi/amazon-emr-managed-scaling-policy-api-openapi.yml, openapi/amazon-emr-notebook-execution-api-openapi.yml,
openapi/amazon-emr-operations-api-openapi.yml, openapi/amazon-emr-security-configuration-api-openapi.yml,
openapi/amazon-emr-session-api-openapi.yml, openapi/amazon-emr-step-api-openapi.yml, openapi/amazon-emr-studio-api-openapi.yml,
openapi/amazon-emr-studio-session-mapping-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: 65
by_action_class:
connected: 16
acting: 49
by_consequence:
read: 16
write: 46
safety-critical: 3
human_in_the_loop_required: 3
operations:
- path: /#GetAutoTerminationPolicy
method: post
operationId: GetAutoTerminationPolicy
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#PutAutoTerminationPolicy
method: post
operationId: PutAutoTerminationPolicy
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: /#RemoveAutoTerminationPolicy
method: post
operationId: RemoveAutoTerminationPolicy
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: /#DescribeCluster
method: post
operationId: DescribeCluster
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: /#ListClusters
method: post
operationId: ListClusters
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ModifyCluster
method: post
operationId: ModifyCluster
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: /#AddInstanceFleet
method: post
operationId: AddInstanceFleet
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: /#ListInstanceFleets
method: post
operationId: ListInstanceFleets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ModifyInstanceFleet
method: post
operationId: ModifyInstanceFleet
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: /#AddInstanceGroups
method: post
operationId: AddInstanceGroups
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: /#ListInstanceGroups
method: post
operationId: ListInstanceGroups
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ModifyInstanceGroups
method: post
operationId: ModifyInstanceGroups
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: /#GetManagedScalingPolicy
method: post
operationId: GetManagedScalingPolicy
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#PutManagedScalingPolicy
method: post
operationId: PutManagedScalingPolicy
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: /#RemoveManagedScalingPolicy
method: post
operationId: RemoveManagedScalingPolicy
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: /#DescribeNotebookExecution
method: post
operationId: DescribeNotebookExecution
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: /#ListNotebookExecutions
method: post
operationId: ListNotebookExecutions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#StartNotebookExecution
method: post
operationId: StartNotebookExecution
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: /#StopNotebookExecution
method: post
operationId: StopNotebookExecution
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: /#GetOnClusterAppUIPresignedURL
method: post
operationId: GetOnClusterAppUIPresignedURL
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#TerminateJobFlows
method: post
operationId: TerminateJobFlows
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: /#TerminateSession
method: post
operationId: TerminateSession
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: /#AddJobFlowSteps
method: post
operationId: AddJobFlowSteps
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: /#AddTags
method: post
operationId: AddTags
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: /#RemoveTags
method: post
operationId: RemoveTags
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: /#CreatePersistentAppUI
method: post
operationId: CreatePersistentAppUI
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: /#DescribePersistentAppUI
method: post
operationId: DescribePersistentAppUI
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: /#DescribeJobFlows
method: post
operationId: DescribeJobFlows
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: /#RunJobFlow
method: post
operationId: RunJobFlow
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: /#DescribeReleaseLabel
method: post
operationId: DescribeReleaseLabel
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: /#ListReleaseLabels
method: post
operationId: ListReleaseLabels
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#GetBlockPublicAccessConfiguration
method: post
operationId: GetBlockPublicAccessConfiguration
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#PutBlockPublicAccessConfiguration
method: post
operationId: PutBlockPublicAccessConfiguration
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: /#GetClusterSessionCredentials
method: post
operationId: GetClusterSessionCredentials
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: /#GetPersistentAppUIPresignedURL
method: post
operationId: GetPersistentAppUIPresignedURL
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#GetSessionEndpoint
method: post
operationId: GetSessionEndpoint
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: /#ListBootstrapActions
method: post
operationId: ListBootstrapActions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListInstances
method: post
operationId: ListInstances
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListSupportedInstanceTypes
method: post
operationId: ListSupportedInstanceTypes
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#PutAutoScalingPolicy
method: post
operationId: PutAutoScalingPolicy
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: /#RemoveAutoScalingPolicy
method: post
operationId: RemoveAutoScalingPolicy
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: /#SetKeepJobFlowAliveWhenNoSteps
method: post
operationId: SetKeepJobFlowAliveWhenNoSteps
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: /#SetTerminationProtection
method: post
operationId: SetTerminationProtection
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: /#SetUnhealthyNodeReplacement
method: post
operationId: SetUnhealthyNodeReplacement
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: /#SetVisibleToAllUsers
method: post
operationId: SetVisibleToAllUsers
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: /#CreateSecurityConfiguration
method: post
operationId: CreateSecurityConfiguration
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: /#DeleteSecurityConfiguration
method: post
operationId: DeleteSecurityConfiguration
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: /#DescribeSecurityConfiguration
method: post
operationId: DescribeSecurityConfiguration
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: /#ListSecurityConfigurations
method: post
operationId: ListSecurityConfigurations
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#GetSession
method: post
operationId: GetSession
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: /#ListSessions
method: post
operationId: ListSessions
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: /#StartSession
method: post
operationId: StartSession
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: /#CancelSteps
method: post
operationId: CancelSteps
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: /#DescribeStep
method: post
operationId: DescribeStep
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: /#ListSteps
method: post
operationId: ListSteps
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateStudio
method: post
operationId: CreateStudio
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: /#DeleteStudio
method: post
operationId: DeleteStudio
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: /#DescribeStudio
method: post
operationId: DescribeStudio
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: /#ListStudios
method: post
operationId: ListStudios
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#UpdateStudio
method: post
operationId: UpdateStudio
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: /#CreateStudioSessionMapping
method: post
operationId: CreateStudioSessionMapping
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: /#DeleteStudioSessionMapping
method: post
operationId: DeleteStudioSessionMapping
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: /#GetStudioSessionMapping
method: post
operationId: GetStudioSessionMapping
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: /#ListStudioSessionMappings
method: post
operationId: ListStudioSessionMappings
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: /#UpdateStudioSessionMapping
method: post
operationId: UpdateStudioSessionMapping
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
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-emr-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/amazon-emr-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.