Amazon Kendra Agentic Access
Amazon Kendra exposes 68 API operations that an AI agent could call, of which 50 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: 18 read, 44 write, and 6 safety-critical.
6 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 | /#CreateAccessControlConfiguration | safety-critical | required |
| POST | /#DeleteAccessControlConfiguration | safety-critical | required |
| POST | /#DescribeAccessControlConfiguration | safety-critical | required |
| POST | /#ListAccessControlConfigurations | safety-critical | required |
| POST | /#StopDataSourceSyncJob | safety-critical | required |
| POST | /#UpdateAccessControlConfiguration | safety-critical | required |
Source
Agentic Access
generated: '2026-11-10'
method: generated
source: openapi/amazon-kendra-access-control-configuration-api-openapi.yml, openapi/amazon-kendra-data-source-sync-job-api-openapi.yml,
openapi/amazon-kendra-data-sources-api-openapi.yml, openapi/amazon-kendra-documents-api-openapi.yml,
openapi/amazon-kendra-experience-api-openapi.yml, openapi/amazon-kendra-faqs-api-openapi.yml,
openapi/amazon-kendra-featured-results-set-api-openapi.yml, openapi/amazon-kendra-indexes-api-openapi.yml,
openapi/amazon-kendra-operations-api-openapi.yml, openapi/amazon-kendra-principal-mapping-api-openapi.yml,
openapi/amazon-kendra-queries-api-openapi.yml, openapi/amazon-kendra-query-suggestions-api-openapi.yml,
openapi/amazon-kendra-query-suggestions-block-list-api-openapi.yml, openapi/amazon-kendra-thesaurus-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: 68
by_action_class:
acting: 50
connected: 18
by_consequence:
safety-critical: 6
read: 18
write: 44
human_in_the_loop_required: 6
operations:
- path: /#CreateAccessControlConfiguration
method: post
operationId: CreateAccessControlConfiguration
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: /#DeleteAccessControlConfiguration
method: post
operationId: DeleteAccessControlConfiguration
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: /#DescribeAccessControlConfiguration
method: post
operationId: DescribeAccessControlConfiguration
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: /#ListAccessControlConfigurations
method: post
operationId: ListAccessControlConfigurations
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: /#UpdateAccessControlConfiguration
method: post
operationId: UpdateAccessControlConfiguration
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: /#ListDataSourceSyncJobs
method: post
operationId: ListDataSourceSyncJobs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#StartDataSourceSyncJob
method: post
operationId: StartDataSourceSyncJob
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: /#StopDataSourceSyncJob
method: post
operationId: StopDataSourceSyncJob
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: /#CreateDataSource
method: post
operationId: CreateDataSource
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: /#DeleteDataSource
method: post
operationId: DeleteDataSource
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: /#DescribeDataSource
method: post
operationId: DescribeDataSource
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: /#ListDataSources
method: post
operationId: ListDataSources
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#UpdateDataSource
method: post
operationId: UpdateDataSource
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: /#BatchDeleteDocument
method: post
operationId: BatchDeleteDocument
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: /#BatchPutDocument
method: post
operationId: BatchPutDocument
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: /#CreateExperience
method: post
operationId: CreateExperience
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: /#DeleteExperience
method: post
operationId: DeleteExperience
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: /#DescribeExperience
method: post
operationId: DescribeExperience
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: /#ListExperiences
method: post
operationId: ListExperiences
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#UpdateExperience
method: post
operationId: UpdateExperience
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: /#CreateFaq
method: post
operationId: CreateFaq
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: /#DeleteFaq
method: post
operationId: DeleteFaq
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: /#DescribeFaq
method: post
operationId: DescribeFaq
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: /#ListFaqs
method: post
operationId: ListFaqs
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#BatchDeleteFeaturedResultsSet
method: post
operationId: BatchDeleteFeaturedResultsSet
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: /#CreateFeaturedResultsSet
method: post
operationId: CreateFeaturedResultsSet
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: /#DescribeFeaturedResultsSet
method: post
operationId: DescribeFeaturedResultsSet
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: /#ListFeaturedResultsSets
method: post
operationId: ListFeaturedResultsSets
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#UpdateFeaturedResultsSet
method: post
operationId: UpdateFeaturedResultsSet
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: /#CreateIndex
method: post
operationId: CreateIndex
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: /#DeleteIndex
method: post
operationId: DeleteIndex
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: /#DescribeIndex
method: post
operationId: DescribeIndex
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: /#UpdateIndex
method: post
operationId: UpdateIndex
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: /#ClearQuerySuggestions
method: post
operationId: ClearQuerySuggestions
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: /#Query
method: post
operationId: Query
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#Retrieve
method: post
operationId: Retrieve
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#SubmitFeedback
method: post
operationId: SubmitFeedback
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: /#AssociateEntitiesToExperience
method: post
operationId: AssociateEntitiesToExperience
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: /#DisassociateEntitiesFromExperience
method: post
operationId: DisassociateEntitiesFromExperience
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: /#AssociatePersonasToEntities
method: post
operationId: AssociatePersonasToEntities
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: /#DisassociatePersonasFromEntities
method: post
operationId: DisassociatePersonasFromEntities
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: /#BatchGetDocumentStatus
method: post
operationId: BatchGetDocumentStatus
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: /#DescribeQuerySuggestionsConfig
method: post
operationId: DescribeQuerySuggestionsConfig
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: /#UpdateQuerySuggestionsConfig
method: post
operationId: UpdateQuerySuggestionsConfig
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: /#GetSnapshots
method: post
operationId: GetSnapshots
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListEntityPersonas
method: post
operationId: ListEntityPersonas
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListExperienceEntities
method: post
operationId: ListExperienceEntities
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListGroupsOlderThanOrderingId
method: post
operationId: ListGroupsOlderThanOrderingId
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListIndices
method: post
operationId: ListIndices
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListTagsForResource
method: post
operationId: ListTagsForResource
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#ListThesauri
method: post
operationId: ListThesauri
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- 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: /#DeletePrincipalMapping
method: post
operationId: DeletePrincipalMapping
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: /#DescribePrincipalMapping
method: post
operationId: DescribePrincipalMapping
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: /#PutPrincipalMapping
method: post
operationId: PutPrincipalMapping
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: /#Query
method: post
operationId: Query
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#Retrieve
method: post
operationId: Retrieve
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#GetQuerySuggestions
method: post
operationId: GetQuerySuggestions
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#CreateQuerySuggestionsBlockList
method: post
operationId: CreateQuerySuggestionsBlockList
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: /#DeleteQuerySuggestionsBlockList
method: post
operationId: DeleteQuerySuggestionsBlockList
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: /#DescribeQuerySuggestionsBlockList
method: post
operationId: DescribeQuerySuggestionsBlockList
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: /#ListQuerySuggestionsBlockLists
method: post
operationId: ListQuerySuggestionsBlockLists
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /#UpdateQuerySuggestionsBlockList
method: post
operationId: UpdateQuerySuggestionsBlockList
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: /#CreateThesaurus
method: post
operationId: CreateThesaurus
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: /#DeleteThesaurus
method: post
operationId: DeleteThesaurus
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: /#DescribeThesaurus
method: post
operationId: DescribeThesaurus
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: /#UpdateThesaurus
method: post
operationId: UpdateThesaurus
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-kendra-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/amazon-kendra-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.