Cognee · Agentic Access

Cognee Agentic Access

x-agentic-access generated

Cognee exposes 136 API operations that an AI agent could call, of which 66 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: 70 read, 61 write, 1 physical, and 4 safety-critical.

4 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.

Artificial IntelligenceMemoryKnowledge GraphRAGAgentsGraph DatabaseVector SearchLLMOpen Source
Operations: 136 Acting: 66 Human-in-the-loop: 4 Method: generated

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

read 70 write 61 physical 1 safety-critical 4

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.

MethodPathConsequenceRecommended human-in-loop
POST /api/v1/auth/forgot-password safety-critical required
POST /api/v1/auth/reset-password safety-critical required
DELETE /api/v1/permissions/capabilities/{principal_id} safety-critical required
DELETE /api/v1/permissions/datasets/{principal_id} safety-critical required
POST /api/v1/integrations/plugins/{plugin_key}/provision physical conditional

Source

Agentic Access

Raw ↑
generated: '2026-11-10'
method: generated
source: openapi/cognee-activity-api-openapi.yml, openapi/cognee-add-api-openapi.yml, openapi/cognee-agent-connections-api-openapi.yml,
  openapi/cognee-agent-management-api-openapi.yml, openapi/cognee-auth-api-openapi.yml, openapi/cognee-checks-api-openapi.yml,
  openapi/cognee-cognify-api-openapi.yml, openapi/cognee-configuration-api-openapi.yml, openapi/cognee-datasets-api-openapi.yml,
  openapi/cognee-delete-api-openapi.yml, openapi/cognee-forget-api-openapi.yml, openapi/cognee-health-api-openapi.yml,
  openapi/cognee-improve-api-openapi.yml, openapi/cognee-integrations-api-openapi.yml, openapi/cognee-llm-api-openapi.yml,
  openapi/cognee-memify-api-openapi.yml, openapi/cognee-ontologies-api-openapi.yml, openapi/cognee-permissions-api-openapi.yml,
  openapi/cognee-recall-api-openapi.yml, openapi/cognee-remember-api-openapi.yml, openapi/cognee-responses-api-openapi.yml,
  openapi/cognee-schema-api-openapi.yml, openapi/cognee-search-api-openapi.yml, openapi/cognee-sessions-api-openapi.yml,
  openapi/cognee-settings-api-openapi.yml, openapi/cognee-skills-api-openapi.yml, openapi/cognee-slack-api-openapi.yml,
  openapi/cognee-sync-api-openapi.yml, openapi/cognee-update-api-openapi.yml, openapi/cognee-users-api-openapi.yml,
  openapi/cognee-validate-api-openapi.yml, openapi/cognee-visualize-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: 136
  by_action_class:
    connected: 70
    acting: 66
  by_consequence:
    read: 70
    write: 61
    safety-critical: 4
    physical: 1
  human_in_the_loop_required: 4
operations:
- path: /api/v1/activity/pipeline-runs
  method: get
  operationId: get_pipeline_runs_api_v1_activity_pipeline_runs_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/activity/spans
  method: get
  operationId: get_spans_api_v1_activity_spans_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/activity/users
  method: get
  operationId: get_tenant_users_api_v1_activity_users_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/activity/agents
  method: get
  operationId: get_agents_api_v1_activity_agents_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/activity/export/{dataset_id}
  method: get
  operationId: export_dataset_markdown_api_v1_activity_export__dataset_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/add
  method: post
  operationId: add_api_v1_add_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: /api/v1/agents/connections
  method: get
  operationId: list_agents_connections_api_v1_agents_connections_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/agents/connections/me
  method: get
  operationId: get_my_connection_detail_api_v1_agents_connections_me_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/agents/connections/{agent_id}
  method: get
  operationId: get_connection_detail_api_v1_agents_connections__agent_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/agents/register
  method: post
  operationId: register_agent_endpoint_api_v1_agents_register_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: /api/v1/agents/unregister
  method: post
  operationId: unregister_agent_endpoint_api_v1_agents_unregister_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: /api/v1/agents/list
  method: get
  operationId: list_agents_endpoint_api_v1_agents_list_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/agents/create
  method: post
  operationId: create_agent_endpoint_api_v1_agents_create_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: /api/v1/agents/{agent_id}
  method: get
  operationId: get_agent_endpoint_api_v1_agents__agent_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/agents/{agent_id}
  method: delete
  operationId: delete_agent_endpoint_api_v1_agents__agent_id__delete
  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/auth/login
  method: post
  operationId: login_api_v1_auth_login_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: /api/v1/auth/logout
  method: post
  operationId: logout_api_v1_auth_logout_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: /api/v1/auth/me
  method: get
  operationId: get_me_api_v1_auth_me_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/auth/register
  method: post
  operationId: register_register_api_v1_auth_register_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: /api/v1/auth/forgot-password
  method: post
  operationId: reset_forgot_password_api_v1_auth_forgot_password_post
  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/auth/reset-password
  method: post
  operationId: reset_reset_password_api_v1_auth_reset_password_post
  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/auth/request-verify-token
  method: post
  operationId: verify_request_token_api_v1_auth_request_verify_token_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: /api/v1/auth/verify
  method: post
  operationId: verify_verify_api_v1_auth_verify_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: /api/v1/auth/api-keys
  method: get
  operationId: get_api_keys_for_user_api_v1_auth_api_keys_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/auth/api-keys
  method: post
  operationId: create_api_key_for_user_api_v1_auth_api_keys_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: /api/v1/auth/api-keys/{api_key_id}
  method: delete
  operationId: delete_api_key_for_user_api_v1_auth_api_keys__api_key_id__delete
  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/checks/connection
  method: post
  operationId: get_connection_check_endpoint_api_v1_checks_connection_post
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/cognify
  method: post
  operationId: cognify_api_v1_cognify_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: /api/v1/configuration/store_user_configuration
  method: post
  operationId: store_user_configuration_api_v1_configuration_store_user_configuration_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: /api/v1/configuration/get_user_configuration/{config_id}
  method: get
  operationId: get_user_configuration_api_v1_configuration_get_user_configuration__config_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/configuration/get_user_configuration/
  method: get
  operationId: get_user_all_configuration_api_v1_configuration_get_user_configuration__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets
  method: get
  operationId: get_datasets_api_v1_datasets_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets
  method: post
  operationId: create_new_dataset_api_v1_datasets_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: /api/v1/datasets
  method: delete
  operationId: delete_all_api_v1_datasets_delete
  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/datasets/{dataset_id}
  method: delete
  operationId: delete_dataset_api_v1_datasets__dataset_id__delete
  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/datasets/{dataset_id}/data/{data_id}
  method: delete
  operationId: delete_data_api_v1_datasets__dataset_id__data__data_id__delete
  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/datasets/{dataset_id}/graph
  method: get
  operationId: get_dataset_graph_api_v1_datasets__dataset_id__graph_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/{dataset_id}/data
  method: get
  operationId: get_dataset_data_api_v1_datasets__dataset_id__data_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/{dataset_id}/data/count
  method: get
  operationId: get_dataset_data_count_api_v1_datasets__dataset_id__data_count_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/status
  method: get
  operationId: get_dataset_status_api_v1_datasets_status_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/status/progress
  method: get
  operationId: get_dataset_progress_api_v1_datasets_status_progress_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/graph-summary
  method: get
  operationId: get_datasets_graph_summary_api_v1_datasets_graph_summary_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/{dataset_id}/data/{data_id}/raw
  method: get
  operationId: get_raw_data_api_v1_datasets__dataset_id__data__data_id__raw_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/{dataset_id}/schema
  method: get
  operationId: get_dataset_schema_api_v1_datasets__dataset_id__schema_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/datasets/{dataset_id}/schema
  method: put
  operationId: update_dataset_schema_api_v1_datasets__dataset_id__schema_put
  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/datasets/{dataset_id}/processing-status
  method: get
  operationId: get_dataset_processing_status_api_v1_datasets__dataset_id__processing_status_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/delete
  method: delete
  operationId: delete_api_v1_delete_delete
  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/forget
  method: post
  operationId: forget_endpoint_api_v1_forget_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: /health
  method: get
  operationId: health_check_health_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /health/detailed
  method: get
  operationId: detailed_health_check_health_detailed_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /
  method: get
  operationId: root__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/improve
  method: post
  operationId: improve_api_v1_improve_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: /api/v1/integrations/status
  method: get
  operationId: integrations_status_api_v1_integrations_status_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/integrations/plugins/{plugin_key}/provision
  method: post
  operationId: provision_plugin_api_v1_integrations_plugins__plugin_key__provision_post
  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: /api/v1/integrations/plugins/{plugin_key}
  method: delete
  operationId: disconnect_plugin_api_v1_integrations_plugins__plugin_key__delete
  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/integrations/{provider}/authorize
  method: post
  operationId: authorize_api_v1_integrations__provider__authorize_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: /api/v1/integrations/{provider}/connection
  method: get
  operationId: connection_status_api_v1_integrations__provider__connection_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/integrations/{provider}/connection
  method: delete
  operationId: disconnect_api_v1_integrations__provider__connection_delete
  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/integrations/{provider}/labels
  method: get
  operationId: integration_resources_api_v1_integrations__provider__labels_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/integrations/{provider}/labels
  method: put
  operationId: set_integration_resources_api_v1_integrations__provider__labels_put
  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/integrations/{provider}/folders
  method: get
  operationId: integration_resources_api_v1_integrations__provider__folders_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/integrations/{provider}/folders
  method: put
  operationId: set_integration_resources_api_v1_integrations__provider__folders_put
  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/integrations/{provider}/resources
  method: get
  operationId: integration_resources_api_v1_integrations__provider__resources_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/integrations/{provider}/resources
  method: put
  operationId: set_integration_resources_api_v1_integrations__provider__resources_put
  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/integrations/{provider}/sync
  method: post
  operationId: sync_integration_api_v1_integrations__provider__sync_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: /api/v1/llm/custom-prompt
  method: post
  operationId: generate_custom_prompt_api_v1_llm_custom_prompt_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: /api/v1/llm/infer-schema
  method: post
  operationId: infer_schema_api_v1_llm_infer_schema_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: /api/v1/memify
  method: post
  operationId: memify_api_v1_memify_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: /api/v1/ontologies
  method: get
  operationId: list_ontologies_api_v1_ontologies_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/ontologies
  method: post
  operationId: upload_ontology_api_v1_ontologies_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: /api/v1/ontologies/{ontology_key}
  method: delete
  operationId: delete_ontology_api_v1_ontologies__ontology_key__delete
  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/permissions/datasets/{principal_id}
  method: post
  operationId: give_datasets_permission_to_principal_api_v1_permissions_datasets__principal_id__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: /api/v1/permissions/datasets/{principal_id}
  method: delete
  operationId: revoke_datasets_permission_from_principal_api_v1_permissions_datasets__principal_id__delete
  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/permissions/principals/{principal_id}/datasets
  method: get
  operationId: get_principal_datasets_api_v1_permissions_principals__principal_id__datasets_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/roles
  method: post
  operationId: create_role_api_v1_permissions_roles_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: /api/v1/permissions/roles/{role_id}
  method: delete
  operationId: delete_role_endpoint_api_v1_permissions_roles__role_id__delete
  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/permissions/users/{user_id}/roles
  method: post
  operationId: add_user_to_role_api_v1_permissions_users__user_id__roles_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: /api/v1/permissions/users/{user_id}/roles
  method: delete
  operationId: remove_user_from_role_endpoint_api_v1_permissions_users__user_id__roles_delete
  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/permissions/users/{user_id}/tenants
  method: post
  operationId: add_user_to_tenant_api_v1_permissions_users__user_id__tenants_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: /api/v1/permissions/tenants/{tenant_id}/users/{user_id}
  method: delete
  operationId: remove_user_from_tenant_endpoint_api_v1_permissions_tenants__tenant_id__users__user_id__delete
  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/permissions/tenants
  method: post
  operationId: create_tenant_api_v1_permissions_tenants_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: /api/v1/permissions/tenants/select
  method: post
  operationId: select_tenant_api_v1_permissions_tenants_select_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: /api/v1/permissions/tenants/{tenant_id}/roles
  method: get
  operationId: get_tenant_roles_api_v1_permissions_tenants__tenant_id__roles_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/tenants/{tenant_id}/roles/{role_id}/users
  method: get
  operationId: get_users_in_role_api_v1_permissions_tenants__tenant_id__roles__role_id__users_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/tenants/{tenant_id}/roles/users/{user_id}
  method: get
  operationId: get_user_roles_api_v1_permissions_tenants__tenant_id__roles_users__user_id__get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/tenants/{tenant_id}/users
  method: get
  operationId: get_users_in_tenant_api_v1_permissions_tenants__tenant_id__users_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/tenants/me
  method: get
  operationId: get_my_tenants_api_v1_permissions_tenants_me_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/tenants/{tenant_id}/capabilities/me
  method: get
  operationId: get_my_capabilities_in_tenant_api_v1_permissions_tenants__tenant_id__capabilities_me_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/permissions/capabilities/{principal_id}
  method: post
  operationId: give_capability_to_principal_api_v1_permissions_capabilities__principal_id__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: /api/v1/permissions/capabilities/{principal_id}
  method: delete
  operationId: revoke_capability_from_principal_api_v1_permissions_capabilities__principal_id__delete
  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/recall
  method: get
  operationId: get_recall_history_api_v1_recall_get
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v1/recall
  method: post
  operationId: recall_api_v1_recall_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


# --- truncated at 32 KB (44 KB total) ---
# Full source: https://artifacts.apis.io/cognee/agentic-access/cognee-agentic-access.yml

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.
All 92 tools →

Call it yourself

curl for this page
Search the catalog
curl "https://apis.io/api/v1/search?q=cognee-agentic-access&limit=10"
Everything under a tag
curl "https://apis.io/api/v1/tags/cognee-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.