Microsoft Office Suite Agentic Access

x-agentic-access generated

Microsoft Office Suite exposes 15 API operations that an AI agent could call, of which 4 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: 11 read, 2 write, and 2 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.

CloudCollaborationDocumentsMicrosoft 365OfficeProductivity

Operations: 15 Acting: 4 Human-in-the-loop: 0 Method: generated

By consequence

read 11 write 2 physical 2

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	/me/sendMail	physical	conditional
POST	/teams/{team_id}/channels/{channel_id}/messages	physical	conditional

Source

Agentic Access

generated: '2026-07-15'
method: generated
source: openapi/microsoft-office-suite-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: 15
  by_action_class:
    connected: 11
    acting: 4
  by_consequence:
    read: 11
    physical: 2
    write: 2
  human_in_the_loop_required: 0
operations:
- path: /me/messages
  method: get
  operationId: listMyMessages
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/messages/{id}
  method: get
  operationId: getMyMessage
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/sendMail
  method: post
  operationId: sendMyMail
  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: /me/mailFolders
  method: get
  operationId: listMyMailFolders
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/drive
  method: get
  operationId: getMyDrive
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/drive/root/children
  method: get
  operationId: listMyDriveRootChildren
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/drive/items/{item_id}
  method: get
  operationId: getMyDriveItem
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/drive/items/{item_id}/content
  method: get
  operationId: downloadMyDriveItemContent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /me/drive/items/{item_id}/content
  method: put
  operationId: uploadMyDriveItemContent
  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: /me/joinedTeams
  method: get
  operationId: listMyJoinedTeams
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /teams/{team_id}
  method: get
  operationId: getTeam
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /teams/{team_id}/channels
  method: get
  operationId: listTeamChannels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /teams/{team_id}/channels
  method: post
  operationId: createTeamChannel
  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: /teams/{team_id}/channels/{channel_id}/messages
  method: get
  operationId: listChannelMessages
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /teams/{team_id}/channels/{channel_id}/messages
  method: post
  operationId: sendChannelMessage
  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