Create a new agent. Use this endpoint to define the agent's behavior, appearance, and capabilities through comprehensive configuration options. To learn more about agents, refer to the agents documentation.
Access-control mode: public (any privileged user can read/write), shared (any privileged user can read, only owner can write), private (only owner can read/write). Agents created without an access-control mode default to private.
Values:publicsharedprivate
avatar_colorstring
Optional hex color code for the agent avatar.
avatar_symbolstring
Optional symbol/initials for the agent avatar.
configurationobjectrequired
Configuration settings for the agent.
ai_indicesstring[] · max items: 100
Array of AI indices to associate with the agent.
approvalsobject
Auto-approval defaults applied to every run of this agent.
auto_approved_apisobject
Destructive Elasticsearch or Kibana APIs this agent may call without a user confirmation, keyed by backend.
elasticsearchstring[] · max items: 100
Elasticsearch APIs pre-approved for every run of this agent. Each entry is an exact identifier formed from the namespace and name (for example indices.create), a namespace wildcard (for example indices.*), or * for every Elasticsearch API. Entries are not checked against the known APIs, and one that matches no API has no effect.
kibanastring[] · max items: 100
Kibana APIs pre-approved for every run of this agent. Each entry is an exact identifier formed from the namespace and name (for example alerting.delete-alerting-rule-id), a namespace wildcard (for example alerting.*), or * for every Kibana API. Entries are not checked against the known APIs, and one that matches no API has no effect.
connector_idsstring[] · max items: 100
Array of connector IDs to associate with the agent.
enable_elastic_capabilitiesboolean
When true, enables built-in Elastic capabilities for the agent.
instructionsstring
Optional system instructions that define the agent behavior.
plugin_idsstring[] · max items: 100
Array of plugin IDs to assign to the agent.
post_execution_workflow_idsstring[] · max items: 100
skill_idsstring[] · max items: 100
Array of skill IDs to be available to the agent.
subagent_idsstring[] · max items: 50
Allowlist of subagent IDs this agent may spawn. Missing or empty disables the run_subagent tool. Use '_self' to enable self-fork.
toolsobject[]required
tool_idsstring[]required
Array of tool IDs that the agent can use.
workflow_idsstring[] · max items: 100
descriptionstring · max length: 2000required
Description of what the agent does.
idstring · max length: 64required
Unique identifier for the agent.
labelsstring[]
Optional labels for categorizing and organizing agents.