H2O.ai · Agentic Access

H2O.ai Agentic Access

x-agentic-access generated

H2O.ai exposes 429 API operations that an AI agent could call, of which 255 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: 174 read, 235 write, 5 physical, and 15 safety-critical.

15 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.

CompanyArtificial IntelligenceMachine LearningMLOpsGenerative AILLMRAGData ScienceModel DeploymentAI AgentsEnterprise AI
Operations: 429 Acting: 255 Human-in-the-loop: 15 Method: generated

By consequence

read 174 write 235 physical 5 safety-critical 15

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.

MethodPathConsequenceHuman-in-loop
DELETE /admin/sessions/{session_id} safety-critical required
POST /ai_assistants/{assistant_id}/stop safety-critical required
DELETE /ai_assistants/{assistant_id}/tool safety-critical required
POST /collections/reset_all_collection_expirations safety-critical required
DELETE /collections/{collection_id}/prompt_settings safety-critical required
PUT /extractors/{extractor_id}/group_permissions safety-critical required
PUT /extractors/{extractor_id}/permissions safety-critical required
DELETE /groups/{group_id}/roles safety-critical required
POST /jobs/{job_id}/cancel safety-critical required
POST /messages/{question_id}/stop safety-critical required
PUT /prompt_templates/{prompt_template_id}/group_permissions safety-critical required
PUT /prompt_templates/{prompt_template_id}/permissions safety-critical required
POST /user_jobs/{job_id}/cancel safety-critical required
POST /users/{user_id}/configurations/{key_name}/reset safety-critical required
DELETE /users/{user_id}/roles safety-critical required
POST /ai_assistants/{assistant_id}/messages physical conditional
POST /ai_assistants/{assistant_id}/send_to_assistant physical conditional
POST /messages/{question_id}/hitl physical conditional
POST /models/{model_name}/answer_question physical conditional
POST /showcase/reorder physical conditional

Source

Agentic Access

Raw ↑ 
generated: '2026-09-23'
method: generated
source: openapi/h2o-ai-admin-sessions-api-openapi.yml, openapi/h2o-ai-agents-api-openapi.yml,
  openapi/h2o-ai-ai-assistants-api-openapi.yml, openapi/h2o-ai-api-keys-api-openapi.yml, openapi/h2o-ai-chat-api-openapi.yml,
  openapi/h2o-ai-collections-api-openapi.yml, openapi/h2o-ai-configurations-api-openapi.yml,
  openapi/h2o-ai-document-ingestion-api-openapi.yml, openapi/h2o-ai-documents-api-openapi.yml,
  openapi/h2o-ai-extractors-api-openapi.yml, openapi/h2o-ai-forums-api-openapi.yml, openapi/h2o-ai-graphrag-api-openapi.yml,
  openapi/h2o-ai-guardrails-api-openapi.yml, openapi/h2o-ai-jobs-api-openapi.yml, openapi/h2o-ai-memory-blocks-api-openapi.yml,
  openapi/h2o-ai-model-api-openapi.yml, openapi/h2o-ai-models-api-openapi.yml, openapi/h2o-ai-permissions-api-openapi.yml,
  openapi/h2o-ai-prompt-templates-api-openapi.yml, openapi/h2o-ai-scheduled-tasks-api-openapi.yml,
  openapi/h2o-ai-secrets-api-openapi.yml, openapi/h2o-ai-shared-chats-api-openapi.yml, openapi/h2o-ai-showcase-api-openapi.yml,
  openapi/h2o-ai-system-api-openapi.yml, openapi/h2o-ai-tags-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: 429
  by_action_class:
    connected: 174
    acting: 255
  by_consequence:
    read: 174
    safety-critical: 15
    write: 235
    physical: 5
  human_in_the_loop_required: 15
operations:
- path: /admin/sessions
  method: get
  operationId: list_admin_sessions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /admin/sessions/stats
  method: get
  operationId: get_admin_sessions_stats
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /admin/sessions/{session_id}
  method: delete
  operationId: revoke_admin_session
  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: /agents
  method: get
  operationId: get_all_agents
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/directory_stats
  method: get
  operationId: list_agent_directory_stats
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/tools
  method: get
  operationId: list_agent_tools
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/tool_preference
  method: get
  operationId: list_agent_tool_preference
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/tool_preference
  method: post
  operationId: update_agent_tool_preference
  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: /agents/tool_preference
  method: delete
  operationId: delete_agent_tool_preference
  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: /agents/keys
  method: get
  operationId: list_agent_keys
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/keys
  method: post
  operationId: create_agent_key
  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: /agents/keys/{key_id}
  method: post
  operationId: update_agent_key
  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: /agents/keys/{key_ids}
  method: delete
  operationId: delete_agent_keys
  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: /agents/tool_association
  method: get
  operationId: list_agent_key_tool_associations
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/tool_association
  method: post
  operationId: create_agent_key_tool_associations
  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: /agents/tool_association/{associate_ids}
  method: delete
  operationId: delete_agent_tool_association
  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: /agents/custom_agent_tool_associations
  method: get
  operationId: list_custom_agent_tool_associations
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_agent_tool_associations
  method: post
  operationId: create_custom_agent_tool_association
  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: /agents/custom_agent_tool_associations/{association_ids}
  method: delete
  operationId: delete_custom_agent_tool_associations
  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: /agents/custom_agent_key_associations
  method: get
  operationId: list_custom_agent_key_associations
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_agent_key_associations
  method: post
  operationId: create_custom_agent_key_association
  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: /agents/custom_agent_key_associations/{association_ids}
  method: delete
  operationId: delete_custom_agent_key_associations
  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: /agents/custom_agents/{agent_id}/suggestions
  method: get
  operationId: get_agent_suggestions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_tools
  method: post
  operationId: add_custom_agent_tool
  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: /agents/custom_tools
  method: get
  operationId: list_custom_agent_tools
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_tools/{tool_ids}
  method: delete
  operationId: delete_custom_agent_tool
  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: /agents/custom_tools/{tool_id}
  method: get
  operationId: get_custom_agent_tool
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_tools/{tool_id}
  method: put
  operationId: update_custom_agent_tool
  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: /agents/custom_tools/{tool_id}/download
  method: get
  operationId: download_custom_agent_tool
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_agents
  method: post
  operationId: add_custom_agent
  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: /agents/custom_agents
  method: get
  operationId: list_custom_agents
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_agents/{agent_ids}
  method: delete
  operationId: delete_custom_agent
  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: /agents/custom_agents/{agent_id}
  method: get
  operationId: get_custom_agent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/custom_agents/{agent_id}
  method: put
  operationId: update_custom_agent
  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: /agents/custom_agents/{agent_id}/download
  method: get
  operationId: download_custom_agent
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/mcp/inspect_tool
  method: post
  operationId: inspect_mcp_tool
  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: /agents/mcp/list_tools
  method: post
  operationId: list_mcp_tools
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/mcp/sdk_options
  method: get
  operationId: get_mcp_sdk_options
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/builtin_mcps
  method: get
  operationId: list_builtin_mcps
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /agents/builtin_mcps/add
  method: post
  operationId: add_builtin_mcp
  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: /agents/builtin_mcps/admin
  method: post
  operationId: create_user_builtin_mcp
  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: /agents/builtin_mcps/admin/{mcp_id}
  method: put
  operationId: update_user_builtin_mcp
  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: /agents/builtin_mcps/admin/{mcp_id}
  method: delete
  operationId: delete_user_builtin_mcp
  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: /agents/builtin_mcps/admin/{mcp_id}/logo
  method: post
  operationId: update_admin_mcp_logo
  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: /agents/builtin_mcps/admin/{mcp_id}/logo
  method: delete
  operationId: remove_admin_mcp_logo
  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: /ai_assistants
  method: post
  operationId: create_ai_assistant
  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: /ai_assistants
  method: get
  operationId: list_ai_assistants
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/generate_spec
  method: post
  operationId: generate_assistant_spec
  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: /ai_assistants/{assistant_id}
  method: get
  operationId: get_ai_assistant
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}
  method: put
  operationId: update_ai_assistant
  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: /ai_assistants/{assistant_id}
  method: delete
  operationId: delete_ai_assistant
  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: /ai_assistants/{assistant_id}/pause
  method: post
  operationId: pause_ai_assistant
  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: /ai_assistants/{assistant_id}/unpause
  method: post
  operationId: unpause_ai_assistant
  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: /ai_assistants/{assistant_id}/start
  method: post
  operationId: start_ai_assistant
  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: /ai_assistants/{assistant_id}/stop
  method: post
  operationId: stop_ai_assistant
  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: /ai_assistants/{assistant_id}/wake
  method: post
  operationId: wake_ai_assistant
  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: /ai_assistants/{assistant_id}/events
  method: get
  operationId: list_ai_assistant_events
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/messages
  method: get
  operationId: list_ai_assistant_messages
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/messages
  method: post
  operationId: send_ai_assistant_message
  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: /ai_assistants/{assistant_id}/permissions/{username}
  method: put
  operationId: share_ai_assistant
  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: /ai_assistants/{assistant_id}/permissions/{username}
  method: delete
  operationId: unshare_ai_assistant
  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: /ai_assistants/{assistant_id}/tool
  method: put
  operationId: update_ai_assistant_tool
  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: /ai_assistants/{assistant_id}/tool
  method: delete
  operationId: reset_ai_assistant_tool
  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: /ai_assistants/{assistant_id}/forums
  method: get
  operationId: list_ai_assistant_forums
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/forums
  method: post
  operationId: connect_ai_assistant_forum
  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: /ai_assistants/{assistant_id}/forums/{forum_id}
  method: delete
  operationId: disconnect_ai_assistant_forum
  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: /ai_assistants/{assistant_id}/collections
  method: get
  operationId: list_ai_assistant_collections
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/collections
  method: post
  operationId: connect_ai_assistant_collection
  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: /ai_assistants/{assistant_id}/collections/{collection_id}
  method: delete
  operationId: disconnect_ai_assistant_collection
  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: /ai_assistants/{assistant_id}/schedules
  method: get
  operationId: list_ai_assistant_schedules
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/schedules
  method: post
  operationId: connect_ai_assistant_schedule
  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: /ai_assistants/{assistant_id}/schedules/{scheduled_task_id}
  method: delete
  operationId: disconnect_ai_assistant_schedule
  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: /ai_assistants/{assistant_id}/files
  method: get
  operationId: list_ai_assistant_files
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/files/{file_id}/content
  method: get
  operationId: download_ai_assistant_file
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/search_forum_posts
  method: get
  operationId: search_assistant_forum_posts
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/history/chat
  method: get
  operationId: get_ai_assistant_chat_history
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/history/events
  method: get
  operationId: get_ai_assistant_event_history
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/permissions
  method: get
  operationId: list_ai_assistant_permissions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /event_types
  method: post
  operationId: create_event_type
  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: /event_types
  method: get
  operationId: list_event_types
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /event_types/{event_type_id}
  method: get
  operationId: get_event_type
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /event_types/{event_type_id}
  method: delete
  operationId: delete_event_type
  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: /ai_assistants/{assistant_id}/event_subscriptions
  method: post
  operationId: subscribe_to_event_type
  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: /ai_assistants/{assistant_id}/event_subscriptions
  method: get
  operationId: list_event_subscriptions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /ai_assistants/{assistant_id}/event_subscriptions/{event_type_id}
  method: delete
  operationId: unsubscribe_from_event_type
  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: /ai_assistants/{assistant_id}/emit_event
  method: post
  operationId: emit_custom_event
  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: /ai_assistants/{assistant_id}/send_to_assistant
  method: post
  operationId: send_inter_assistant_message
  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: /admin/api_keys
  method: post
  operationId: create_api_key_for_user
  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: /admin/api_keys
  method: get
  operationId: list_all_api_keys
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /admin/api_keys/deactivate/{key_id}
  method: post
  operationId: deactivate_api_key
  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: /admin/api_keys/expire/{key_id}
  method: patch
  operationId: update_api_key_expiry
  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: /admin/api_keys/inactivity_interval/{key_id}
  method: patch
  operationId: update_api_key_inactivity_interval
  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: /admin/api_keys/{key_id}
  method: delete
  operationId: delete_api_key
  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: /chats
  method: post
  operationId: create_chat_session
  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: /chats
  method: get
  operationId: list_chat_sessions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /chats/count
  method: get
  operationId: get_chat_session_count
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /chats/delete_job
  method: post
  operationId: create_delete_chat_session_job
  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: /chats/{session_id}
  method: get
  operationId: get_chat_session
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /chats/{session_id}
  method: delete
  operationId: delete_chat_session
  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: /chats/{session_id}
  method: patch
  operationId: update_chat_session
  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 (131 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/h2o-ai/refs/heads/main/agentic-access/h2o-ai-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=h2o-ai-agentic-access&limit=10"
Everything under a tag 
curl "https://apis.io/api/v1/tags/h2o-ai-agentic-access"

Discovery needs no key. Ratings and market analysis are Pro.

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.