Centers for Medicare and Medicaid Services Agentic Access
Centers for Medicare and Medicaid Services exposes 94 API operations that an AI agent could call, of which 21 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: 73 read, 20 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.
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 | Human-in-loop |
|---|---|---|---|
| PUT | /api/v1/admin/client/{contractNumber}/disable | safety-critical | required |
Source
Agentic Access
generated: '2026-08-15'
method: generated
source: openapi/cms-ab2d-openapi.yml, openapi/cms-api-reference-api-openapi.yml, openapi/cms-bcda-openapi.yml,
openapi/cms-bulk-data-api-openapi.yml, openapi/cms-capability-api-openapi.yml, openapi/cms-code-search-api-openapi.yml,
openapi/cms-cost-search-api-openapi.yml, openapi/cms-coverage-api-openapi.yml, openapi/cms-enrollments-api-openapi.yml,
openapi/cms-explanationofbenefit-api-openapi.yml, openapi/cms-geography-api-openapi.yml, openapi/cms-households-eligibility-api-openapi.yml,
openapi/cms-insurance-issuers-api-openapi.yml, openapi/cms-insurance-plans-api-openapi.yml,
openapi/cms-patient-api-openapi.yml, openapi/cms-plans-api-openapi.yml, openapi/cms-provider-drug-coverage-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: 94
by_action_class:
acting: 21
connected: 73
by_consequence:
write: 20
safety-critical: 1
read: 73
human_in_the_loop_required: 1
operations:
- path: /api/v1/admin/client
method: put
operationId: udpateClient
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: /api/v1/admin/client
method: post
operationId: createClient
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: /api/v1/admin/client/{contractNumber}/enable
method: put
operationId: enableClient
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: /api/v1/admin/client/{contractNumber}/disable
method: put
operationId: disableClient
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: /api/v1/admin/job/{contractNumber}
method: post
operationId: createJobByContractOnBehalfOfClient
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: /status
method: get
operationId: getMaintenanceMode
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /health
method: get
operationId: getHealth
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v3/fhir/metadata
method: get
operationId: capabilityStatement
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v3/fhir/Patient/$export
method: get
operationId: exportAllPatients
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v3/fhir/Job/{jobUuid}/file/{filename}
method: get
operationId: downloadFile
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v3/fhir/Job/{jobUuid}/$status
method: get
operationId: getJobStatus
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v3/fhir/Job/{jobUuid}/$status
method: delete
operationId: deleteRequest
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v2/fhir/metadata
method: get
operationId: capabilityStatement_1
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/fhir/Patient/$export
method: get
operationId: exportAllPatients_1
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/fhir/Job/{jobUuid}/file/{filename}
method: get
operationId: downloadFile_1
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/fhir/Job/{jobUuid}/$status
method: get
operationId: getJobStatus_1
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/fhir/Job/{jobUuid}/$status
method: delete
operationId: deleteRequest_1
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: /api/v2/fhir/Group/{contractNumber}/$export
method: get
operationId: exportPatientsWithContract
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/fhir/metadata
method: get
operationId: capabilityStatement_2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/fhir/Patient/$export
method: get
operationId: exportAllPatients_2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/fhir/Job/{jobUuid}/file/{filename}
method: get
operationId: downloadFile_2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/fhir/Job/{jobUuid}/$status
method: get
operationId: getJobStatus_2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/fhir/Job/{jobUuid}/$status
method: delete
operationId: deleteRequest_2
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: /api/v1/fhir/Group/{contractNumber}/$export
method: get
operationId: exportPatientsWithContract_1
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/admin/client/{contractNumber}
method: get
operationId: getClient
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /versions
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /market-years
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /_auth
method: get
operationId: getAuthInfo
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /_version
method: get
operationId: getVersion
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/Group/{groupId}/$export
method: get
operationId: bulkGroupRequest
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/Patient/$export
method: get
operationId: bulkPatientRequest
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/attribution_status
method: get
operationId: attributionStatus
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/jobs
method: get
operationId: jobsStatus
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/jobs/{jobId}
method: get
operationId: jobStatus
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v1/jobs/{jobId}
method: delete
operationId: deleteJob
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /api/v1/metadata
method: get
operationId: metadata
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/Group/{groupId}/$export
method: get
operationId: bulkGroupRequestV2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/Patient/$export
method: get
operationId: bulkPatientRequestv2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/attribution_status
method: get
operationId: attributionStatusv2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/jobs
method: get
operationId: jobsStatusV2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/jobs/{jobId}
method: get
operationId: jobStatusidv2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /api/v2/jobs/{jobId}
method: delete
operationId: deleteJobv2
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: /api/v2/metadata
method: get
operationId: metadatav2
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /auth/token
method: post
operationId: GetAuthToken
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: /auth/welcome
method: get
operationId: welcome
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/{jobId}/{filename}
method: get
operationId: serveData
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/apt
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/decile-mapping
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/state-medicaid
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/rate-areas
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/county-zips
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /data/crosswalk
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /metadata
method: get
operationId: getCapabilityStatement
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /codes/{code}
method: get
operationId: getCodeInformation
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /codes
method: get
operationId: getBatchCodes
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /costs/{code}
method: get
operationId: getCostByCode
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /costs
method: get
operationId: getBatchCosts
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /Coverage
method: get
operationId: searchCoverage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /Coverage/{id}
method: get
operationId: readCoverage
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /enrollment/validate
method: post
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: /ExplanationOfBenefit
method: get
operationId: searchExplanationOfBenefit
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /ExplanationOfBenefit/{id}
method: get
operationId: readExplanationOfBenefit
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /counties/by/zip/{zipcode}
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /counties/{fips}
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /states
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /states/{abbrev}
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /states/{abbrev}/medicaid
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /states/{abbrev}/poverty-guidelines
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /rate-areas
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /households/eligibility/estimates
method: post
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: /households/ichra
method: post
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: /households/lcbp
method: post
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: /households/slcsp
method: post
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: /households/lcsp
method: post
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: /households/pcfpl
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /issuers
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /issuers/{issuer_id}
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /crosswalk
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /plans
method: post
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: /plans/search
method: post
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: /plans/search/stats
method: post
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: /plans/{plan_id}
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /plans/{plan_id}/quality-ratings
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /Patient
method: get
operationId: searchPatient
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /Patient/{id}
method: get
operationId: readPatient
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /plans/{plan_id}
method: post
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: /drugs/autocomplete
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /drugs/search
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /drugs/covered
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /coverage/stats
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /coverage/search
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /providers/autocomplete
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /providers/search
method: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /providers/covered
method: get
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=cms-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/cms-agentic-access"
Discovery needs no key. Ratings and market analysis are Pro.