> ## Documentation Index > Fetch the complete documentation index at: https://docs.corti.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get Agent Card > This endpoint retrieves the agent card in JSON format, which provides metadata about the agent, including its name, description, and the experts it can call. ## OpenAPI ````yaml /agentic/auto-generated-openapi.yml get /agents/{id}/agent-card.json openapi: 3.1.1 info: title: Corti Agent API version: 0.1.0 description: > The Corti Agent API allows users to interact with the Corti Agent, enabling the creation and management of threads, sending messages, and receiving responses. servers: [] security: [] paths: /agents/{id}/agent-card.json: get: tags: - Agents summary: Get Agent Card description: > This endpoint retrieves the agent card in JSON format, which provides metadata about the agent, including its name, description, and the experts it can call. operationId: agents_get_card parameters: - $ref: '#/components/parameters/Tenant-Name' - $ref: '#/components/parameters/AgentID' responses: '200': description: Agent card retrieved successfully. content: application/json: schema: $ref: '#/components/schemas/AgentsAgentCard' '400': description: > The request could not be processed, possibly due to missing required fields or invalid data. content: application/json: schema: $ref: '#/components/schemas/AgentsErrorResponse' '401': description: | Authentication is required to access this endpoint. content: application/json: schema: $ref: '#/components/schemas/AgentsErrorResponse' '404': description: Agent not found. content: application/json: schema: $ref: '#/components/schemas/AgentsErrorResponse' x-codeSamples: - lang: csharp label: C# .NET SDK source: > using Corti; var client = new CortiClient( "TENANT_NAME", CortiClientEnvironment.Eu, new CortiClientAuth.ClientCredentials("client_id", "client_secret") ); await client.Agents.GetCardAsync("12345678-90ab-cdef-gh12-34567890abc"); - lang: javascript label: JavaScript SDK source: | import { CortiClient, CortiEnvironment } from "@corti/sdk"; const client = new CortiClient({ environment: CortiEnvironment.Eu, auth: { clientId: "YOUR_CLIENT_ID", clientSecret: "YOUR_CLIENT_SECRET" }, tenantName: "YOUR_TENANT_NAME" }); await client.agents.getCard("12345678-90ab-cdef-gh12-34567890abc"); components: parameters: Tenant-Name: name: Tenant-Name in: header description: >- Identifies a distinct entity within Corti's multi-tenant system. Ensures correct routing and authentication of the request. required: true example: base schema: type: string description: >- Identifies a distinct entity within Corti's multi-tenant system. Ensures correct routing and authentication of the request. example: base AgentID: name: id in: path required: true description: The identifier of the agent associated with the context. schema: type: string description: The identifier of the agent associated with the context. example: 12345678-90ab-cdef-gh12-34567890abc schemas: AgentsAgentCard: type: object required: - protocolVersion - name - description - url - version - capabilities - defaultInputModes - defaultOutputModes - skills properties: protocolVersion: type: string description: The version of the A2A protocol this agents supports. name: type: string description: The name of the agent. description: type: string description: A human readable description of the agent. url: type: string description: | The URL where the agent can be reached to process messages. preferredTransport: type: - string - 'null' additionalInterfaces: type: - array - 'null' items: $ref: '#/components/schemas/AgentsAgentInterface' description: > A list of additional transport protocols and URL combinations the agent supports. iconUrl: type: - string - 'null' description: | A URL to an icon representing the agent. documentationUrl: type: - string - 'null' description: | A URL to documentation describing how to interact with the agent. provider: oneOf: - $ref: '#/components/schemas/AgentsAgentProvider' - type: 'null' version: type: string description: The version of the agent. capabilities: oneOf: - $ref: '#/components/schemas/AgentsAgentCapabilities' - type: 'null' securitySchemes: type: - object - 'null' description: > A declaration of the security schemes available to authorize requests. The key is the scheme name. Follows the OpenAPI 3.0 Security Scheme Object. security: type: - object - 'null' description: > A list of security requirement objects that apply to all agent interactions. Each object lists security schemes that can be used. Follows the OpenAPI 3.0 Security Requirement Object. This list can be seen as an OR of ANDs. Each object in the list describes one possible set of security requirements that must be present on a request. This allows specifying, for example, "callers must either use OAuth OR an API Key AND mTLS." defaultInputModes: type: array items: type: string description: > Default set of supported input MIME types for all skills, which can be overridden on a per-skill basis. defaultOutputModes: type: array items: type: string description: > Default set of supported output MIME types for all skills, which can be overridden on a per-skill basis. skills: type: array items: $ref: '#/components/schemas/AgentsAgentSkill' description: > The set of skills, or distinct capabilities, that the agent can perform. supportsAuthenticatedExtendedCard: type: - boolean - 'null' description: > Indicates whether the agent supports returning an extended agent card when called with authentication. signatures: type: - array - 'null' items: $ref: '#/components/schemas/AgentsAgentCardSignature' description: | JSON Web Signatures computed for this AgentCard. AgentsErrorResponse: type: object required: - code - description properties: code: type: string description: | A machine-readable error code that identifies the type of error. description: type: string description: > A human-readable description of the error, providing more context about what went wrong. howToFix: type: string description: | A human-readable message describing how to fix the issue. details: type: object description: | An optional object containing additional details about the error. additionalProperties: true cause: type: object description: > An optional object containing the cause of the error, following the same structure as the parent error response. additionalProperties: true AgentsAgentInterface: type: object required: - transport - url properties: url: type: string description: The URL where the agent can be reached using the specified protocol. transport: type: string AgentsAgentProvider: type: object required: - organization - url properties: organization: type: string description: The name of the organization providing the agent. url: type: string description: The URL of the organization providing the agent. AgentsAgentCapabilities: type: object properties: streaming: type: boolean description: | Indicates whether the agent supports streaming responses. pushNotifications: type: boolean description: > Indicates whether the agent supports push notifications for task status updates. stateTransitionHistory: type: boolean description: > Indicates whether the agent maintains a history of state transitions for tasks. extensions: type: - array - 'null' items: $ref: '#/components/schemas/AgentsAgentExtension' description: | A list of protocol extensions supported by the agent. AgentsAgentSkill: type: object required: - id - name - description - tags properties: id: type: string description: Unique identifier for the skill. name: type: string description: The name of the skill. description: type: string description: A brief description of the skill's capabilities. tags: type: array items: type: string description: > A list of tags or keywords associated with the skill, useful for categorization and search. examples: type: - array - 'null' items: $ref: '#/components/schemas/AgentsMessage' description: | A list of example messages that demonstrate how to use this skill. inputModes: type: - array - 'null' items: type: string description: > A list of supported input MIME types for this skill. If omitted, the agent's default input modes apply. outputModes: type: - array - 'null' items: type: string description: > A list of supported output MIME types for this skill. If omitted, the agent's default output modes apply. security: type: - object - 'null' description: > Security schemes necessary for the agent to leverage this skill. As in the overall AgentCard.security, this list represents a logical OR of security requirement objects. Each object is a set of security schemes that must be used together (a logical AND). AgentsAgentCardSignature: type: object required: - protected - signature properties: protected: type: string description: | The protected header of the JWS, base64url-encoded. signature: type: string description: | The JWS signature, base64url-encoded. header: type: object description: | The unprotected header of the JWS, if any. AgentsAgentExtension: type: object required: - uri properties: uri: type: string format: uri description: The URI that identifies the extension. description: type: string description: A brief description of the extension. required: type: boolean description: > If true, the client must understand and comply with the extension's requirements to interact with the agent. params: type: object description: | Optional, extension-specific configuration parameters. AgentsMessage: type: object required: - messageId - role - parts - kind properties: role: type: string description: The role of the message sender. enum: - user - agent parts: type: array items: $ref: '#/components/schemas/AgentsPart' description: The content of the message. metadata: type: object description: Additional metadata for the message. extensions: type: array items: type: string description: Extensions for the message. referenceTaskIds: type: array items: type: string description: Task IDs that this message references for additional context. messageId: type: string description: Unique identifier for the message. taskId: type: string description: Unique identifier for the task associated with the message. contextId: type: string description: Identifier for the context (thread) in which the message is sent. kind: type: string description: The kind of the object, always "message". enum: - message AgentsPart: type: object oneOf: - $ref: '#/components/schemas/AgentsTextPart' - $ref: '#/components/schemas/AgentsFilePart' - $ref: '#/components/schemas/AgentsDataPart' AgentsTextPart: type: object required: - kind - text properties: kind: type: string description: The kind of the part, always "text". enum: - text text: type: string description: The text content of the part. metadata: type: object description: Additional metadata for the text part. AgentsFilePart: type: object required: - kind properties: kind: type: string description: The kind of the part, always "file". enum: - file file: type: object oneOf: - $ref: '#/components/schemas/AgentsFileWithUri' - $ref: '#/components/schemas/AgentsFileWithBytes' metadata: type: object description: Additional metadata for the file part. AgentsDataPart: type: object required: - kind - data properties: kind: type: string description: The kind of the part, always "data". enum: - data data: type: object description: JSON data payload. metadata: type: object description: Additional metadata for the data part. AgentsFileWithUri: type: object required: - uri properties: uri: type: string format: uri description: The URI of the file. name: type: string description: The name of the file. mimeType: type: string description: The MIME type of the file. AgentsFileWithBytes: type: object required: - bytes properties: bytes: type: string format: byte description: The byte content of the file. name: type: string description: The name of the file. mimeType: type: string description: The MIME type of the file. ````