🎉 Join us at the kagent Community Party at KubeCon Atlanta on Nov 12
Documentation

API Reference#

Packages#

kagent.dev/v1alpha2#

Package v1alpha1 contains API Schema definitions for the agent v1alpha1 API group.

Resource Types#

A2AConfig#

Appears in:

FieldDescriptionDefaultValidation
skills AgentSkill arrayMinItems: 1

Agent#

Agent is the Schema for the agents API.

FieldDescriptionDefaultValidation
apiVersion stringkagent.dev/v1alpha2
kind stringAgent
kind stringKind is a string value representing the REST resource this object represents.
Servers may infer this from the endpoint the client submits requests to.
Cannot be updated.
In CamelCase.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
apiVersion stringAPIVersion defines the versioned schema of this representation of an object.
Servers should convert recognized schemas to the latest internal value, and
may reject unrecognized values.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
metadata ObjectMetaRefer to Kubernetes API documentation for fields of metadata.
spec AgentSpec
status AgentStatus

AgentSkill#

Underlying type: AgentSkill

Appears in:

FieldDescriptionDefaultValidation
id stringID is the unique identifier for the skill.
name stringName is the human-readable name of the skill.
description stringDescription is an optional detailed description of the skill.
tags string arrayTags are optional tags for categorization.
examples string arrayExamples are optional usage examples.
inputModes string arrayInputModes are the supported input data modes/types.
outputModes string arrayOutputModes are the supported output data modes/types.

AgentSpec#

AgentSpec defines the desired state of Agent.

Appears in:

FieldDescriptionDefaultValidation
type AgentTypeDeclarativeEnum: [Declarative BYO]
byo BYOAgentSpec
declarative DeclarativeAgentSpec
description string

AgentStatus#

AgentStatus defines the observed state of Agent.

Appears in:

FieldDescriptionDefaultValidation
observedGeneration integer
conditions Condition array

AgentType#

Underlying type: string

AgentType represents the agent type

Validation:

  • Enum: [Declarative BYO]

Appears in:

FieldDescription
Declarative
BYO

AnthropicConfig#

AnthropicConfig contains Anthropic-specific configuration options

Appears in:

FieldDescriptionDefaultValidation
baseUrl stringBase URL for the Anthropic API (overrides default)
maxTokens integerMaximum tokens to generate
temperature stringTemperature for sampling
topP stringTop-p sampling parameter
topK integerTop-k sampling parameter

AnthropicVertexAIConfig#

Appears in:

FieldDescriptionDefaultValidation
projectID stringThe project ID
location stringThe project location
temperature stringTemperature
topP stringTop-p sampling parameter
topK stringTop-k sampling parameter
stopSequences string arrayStop sequences
maxTokens integerMaximum tokens to generate

AzureOpenAIConfig#

AzureOpenAIConfig contains Azure OpenAI-specific configuration options

Appears in:

FieldDescriptionDefaultValidation
azureEndpoint stringEndpoint for the Azure OpenAI API
apiVersion stringAPI version for the Azure OpenAI API
azureDeployment stringDeployment name for the Azure OpenAI API
azureAdToken stringAzure AD token for authentication
temperature stringTemperature for sampling
maxTokens integerMaximum tokens to generate
topP stringTop-p sampling parameter

BYOAgentSpec#

Appears in:

FieldDescriptionDefaultValidation
deployment ByoDeploymentSpecTrust relationship to the agent.

BaseVertexAIConfig#

Appears in:

FieldDescriptionDefaultValidation
projectID stringThe project ID
location stringThe project location
temperature stringTemperature
topP stringTop-p sampling parameter
topK stringTop-k sampling parameter
stopSequences string arrayStop sequences

ByoDeploymentSpec#

Appears in:

FieldDescriptionDefaultValidation
image stringMinLength: 1
cmd string
args string array
replicas integerIf not specified, the default value is 1.1Minimum: 1
imagePullSecrets LocalObjectReference array
volumes Volume array
volumeMounts VolumeMount array
labels object (keys:string, values:string)
annotations object (keys:string, values:string)
env EnvVar array
imagePullPolicy PullPolicy
resources ResourceRequirements

DeclarativeAgentSpec#

Appears in:

FieldDescriptionDefaultValidation
systemMessage stringSystemMessage is a string specifying the system message for the agent
systemMessageFrom ValueSourceSystemMessageFrom is a reference to a ConfigMap or Secret containing the system message.
modelConfig stringThe name of the model config to use.
If not specified, the default value is "default-model-config".
Must be in the same namespace as the Agent.
stream booleanWhether to stream the response from the model.
If not specified, the default value is true.
tools Tool arrayMaxItems: 20
a2aConfig A2AConfigA2AConfig instantiates an A2A server for this agent,
served on the HTTP port of the kagent kubernetes
controller (default 8083).
The A2A server URL will be served at
<kagent-controller-ip>:8083/api/a2a/<agent-namespace>/<agent-name>
Read more about the A2A protocol here: https://github.com/google/A2A
deployment DeclarativeDeploymentSpec

DeclarativeDeploymentSpec#

Appears in:

FieldDescriptionDefaultValidation
imageRegistry string
replicas integerIf not specified, the default value is 1.1Minimum: 1
imagePullSecrets LocalObjectReference array
volumes Volume array
volumeMounts VolumeMount array
labels object (keys:string, values:string)
annotations object (keys:string, values:string)
env EnvVar array
imagePullPolicy PullPolicy
resources ResourceRequirements

GeminiConfig#

Appears in:

GeminiVertexAIConfig#

GeminiVertexAIConfig contains Gemini Vertex AI-specific configuration options

Appears in:

FieldDescriptionDefaultValidation
projectID stringThe project ID
location stringThe project location
temperature stringTemperature
topP stringTop-p sampling parameter
topK stringTop-k sampling parameter
stopSequences string arrayStop sequences
maxOutputTokens integerMaximum output tokens
candidateCount integerCandidate count
responseMimeType stringResponse mime type

MCPTool#

Appears in:

FieldDescriptionDefaultValidation
name string
description string

McpServerTool#

Appears in:

FieldDescriptionDefaultValidation
kind string
apiGroup string
name string
toolNames string arrayThe names of the tools to be provided by the ToolServer
For a list of all the tools provided by the server,
the client can query the status of the ToolServer object after it has been created

ModelConfig#

ModelConfig is the Schema for the modelconfigs API.

FieldDescriptionDefaultValidation
apiVersion stringkagent.dev/v1alpha2
kind stringModelConfig
kind stringKind is a string value representing the REST resource this object represents.
Servers may infer this from the endpoint the client submits requests to.
Cannot be updated.
In CamelCase.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
apiVersion stringAPIVersion defines the versioned schema of this representation of an object.
Servers should convert recognized schemas to the latest internal value, and
may reject unrecognized values.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
metadata ObjectMetaRefer to Kubernetes API documentation for fields of metadata.
spec ModelConfigSpec
status ModelConfigStatus

ModelConfigSpec#

ModelConfigSpec defines the desired state of ModelConfig.

Appears in:

FieldDescriptionDefaultValidation
model string
apiKeySecret stringThe name of the secret that contains the API key. Must be a reference to the name of a secret in the same namespace as the referencing ModelConfig
apiKeySecretKey stringThe key in the secret that contains the API key
defaultHeaders object (keys:string, values:string)
provider ModelProviderThe provider of the modelOpenAIEnum: [Anthropic OpenAI AzureOpenAI Ollama Gemini GeminiVertexAI AnthropicVertexAI]
openAI OpenAIConfigOpenAI-specific configuration
anthropic AnthropicConfigAnthropic-specific configuration
azureOpenAI AzureOpenAIConfigAzure OpenAI-specific configuration
ollama OllamaConfigOllama-specific configuration
gemini GeminiConfigGemini-specific configuration
geminiVertexAI GeminiVertexAIConfigGemini Vertex AI-specific configuration
anthropicVertexAI AnthropicVertexAIConfigAnthropic-specific configuration

ModelConfigStatus#

ModelConfigStatus defines the observed state of ModelConfig.

Appears in:

FieldDescriptionDefaultValidation
conditions Condition array
observedGeneration integer

ModelProvider#

Underlying type: string

ModelProvider represents the model provider type

Validation:

  • Enum: [Anthropic OpenAI AzureOpenAI Ollama Gemini GeminiVertexAI AnthropicVertexAI]

Appears in:

FieldDescription
Anthropic
AzureOpenAI
OpenAI
Ollama
Gemini
GeminiVertexAI
AnthropicVertexAI

OllamaConfig#

OllamaConfig contains Ollama-specific configuration options

Appears in:

FieldDescriptionDefaultValidation
host stringHost for the Ollama API
options object (keys:string, values:string)Options for the Ollama API

OpenAIConfig#

OpenAIConfig contains OpenAI-specific configuration options

Appears in:

FieldDescriptionDefaultValidation
baseUrl stringBase URL for the OpenAI API (overrides default)
organization stringOrganization ID for the OpenAI API
temperature stringTemperature for sampling
maxTokens integerMaximum tokens to generate
topP stringTop-p sampling parameter
frequencyPenalty stringFrequency penalty
presencePenalty stringPresence penalty
seed integerSeed value
n integerN value
timeout integerTimeout

RemoteMCPServer#

RemoteMCPServer is the Schema for the RemoteMCPServers API.

FieldDescriptionDefaultValidation
apiVersion stringkagent.dev/v1alpha2
kind stringRemoteMCPServer
kind stringKind is a string value representing the REST resource this object represents.
Servers may infer this from the endpoint the client submits requests to.
Cannot be updated.
In CamelCase.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
apiVersion stringAPIVersion defines the versioned schema of this representation of an object.
Servers should convert recognized schemas to the latest internal value, and
may reject unrecognized values.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
metadata ObjectMetaRefer to Kubernetes API documentation for fields of metadata.
spec RemoteMCPServerSpec
status RemoteMCPServerStatus

RemoteMCPServerProtocol#

Underlying type: string

Validation:

  • Enum: [SSE STREAMABLE_HTTP]

Appears in:

FieldDescription
SSE
STREAMABLE_HTTP

RemoteMCPServerSpec#

RemoteMCPServerSpec defines the desired state of RemoteMCPServer.

Appears in:

FieldDescriptionDefaultValidation
description string
protocol RemoteMCPServerProtocolSTREAMABLE_HTTPEnum: [SSE STREAMABLE_HTTP]
url stringMinLength: 1
headersFrom ValueRef array
timeout Duration
sseReadTimeout Duration
terminateOnClose booleantrue

RemoteMCPServerStatus#

RemoteMCPServerStatus defines the observed state of RemoteMCPServer.

Appears in:

FieldDescriptionDefaultValidation
observedGeneration integerINSERT ADDITIONAL STATUS FIELD - define observed state of cluster
Important: Run "make" to regenerate code after modifying this file
conditions Condition array
discoveredTools MCPTool arrayOptional: {}

SharedDeploymentSpec#

Appears in:

FieldDescriptionDefaultValidation
replicas integerIf not specified, the default value is 1.1Minimum: 1
imagePullSecrets LocalObjectReference array
volumes Volume array
volumeMounts VolumeMount array
labels object (keys:string, values:string)
annotations object (keys:string, values:string)
env EnvVar array
imagePullPolicy PullPolicy
resources ResourceRequirements

Tool#

Appears in:

FieldDescriptionDefaultValidation
type ToolProviderTypeEnum: [McpServer Agent]
mcpServer McpServerTool
agent TypedLocalReference
headersFrom ValueRef arrayHeadersFrom specifies a list of configuration values to be added as
headers to requests sent to the Tool from this agent. The value of
each header is resolved from either a Secret or ConfigMap in the same
namespace as the Agent. Headers specified here will override any
headers of the same name/key specified on the tool.

ToolProviderType#

Underlying type: string

ToolProviderType represents the tool provider type

Validation:

  • Enum: [McpServer Agent]

Appears in:

FieldDescription
McpServer
Agent

TypedLocalReference#

Appears in:

FieldDescriptionDefaultValidation
kind string
apiGroup string
name string

ValueRef#

ValueRef represents a configuration value

Appears in:

FieldDescriptionDefaultValidation
name string
value string
valueFrom ValueSource

ValueSource#

ValueSource defines a source for configuration values from a Secret or ConfigMap

Appears in:

FieldDescriptionDefaultValidation
type ValueSourceTypeEnum: [ConfigMap Secret]
name stringThe name of the ConfigMap or Secret.
key stringThe key of the ConfigMap or Secret.

ValueSourceType#

Underlying type: string

Appears in:

FieldDescription
ConfigMap
Secret
Kagent Lab: Discover kagent and kmcp
Free, on‑demand lab: build custom AI agents with kagent and integrate tools via kmcp on Kubernetes.