Claude Platform Docs

Crea agente

$client->beta->agents->create(Model model, string name, ?string description, ?BetaManagedAgentsExecutionIdentityParams executionIdentity, ?list<BetaManagedAgentsURLMCPServerParams> mcpServers, ?array<string,string> metadata, ?BetaManagedAgentsMultiagentParams multiagent, ?list<BetaManagedAgentsSkillParams> skills, ?string system, ?list<Tool> tools, ?list<AnthropicBeta> betas, ?string workspaceID): BetaManagedAgentsAgent
POST/v1/agents
Requires anthropic-beta: managed-agents-2026-04-01. How to send beta headers

Crea agente

Parameters
model: Model

Model identifier. Accepts the model string, e.g. claude-opus-5-5, or a model_config object for additional configuration control

name: string

Human-readable name for the agent.

description?: optional string

Description of what the agent does.

executionIdentity?: optional BetaManagedAgentsExecutionIdentityParams

Execution principal for runs of this agent. Omitting it, sending null, or sending {"type": "service_account"} stores the default.

mcpServers?: optional list<BetaManagedAgentsURLMCPServerParams>

MCP servers this agent connects to. Maximum 20. Names must be unique within the array. Every server must be referenced by an mcp_toolset in tools; unreferenced servers are rejected. See the MCP connector guide.

metadata?: optional array<string,string>

Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars.

multiagent?: optional BetaManagedAgentsMultiagentParams

Multiagent orchestration configuration.

skills?: optional list<BetaManagedAgentsSkillParams>

Skills available to the agent.

system?: optional string

System prompt for the agent.

tools?: optional list<Tool>

Tool configurations available to the agent. Maximum of 256 tools across all toolsets allowed.

betas?: optional list<AnthropicBeta>⁠Header parameter

This endpoint is in beta: requests must send managed-agents-2026-04-01 in this header.

workspaceID?: optional string⁠Header parameter

Optional header to select the Workspace for this request. The value is a Workspace ID (for example, wrkspc_011CZkZaBF1tNoB5wlCeusgy).

Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.

Returns
class BetaManagedAgentsAgent { $type = 'agent'; $id; $archivedAt; /* 13 more */ }
Crea agente
<?php

require_once dirname(__DIR__) . '/vendor/autoload.php';

use Anthropic\Client;
use Anthropic\Beta\AnthropicBeta;
use Anthropic\Beta\Agents\BetaManagedAgentsModel;

$client = new Client(apiKey: 'my-anthropic-api-key');

$betaManagedAgentsAgent = $client->beta->agents->create(
  model: BetaManagedAgentsModel::CLAUDE_OPUS_5_5,
  name: 'My First Agent',
  description: 'A general-purpose starter agent.',
  executionIdentity: [
    'roleARN' => 'arn:aws:iam::228601553692:role/T', 'type' => 'aws_role'
  ],
  mcpServers: [
    [
      'name' => 'example-mcp',
      'type' => 'url',
      'url' => 'https://example-server.modelcontextprotocol.io/sse',
    ],
  ],
  metadata: ['foo' => 'bar'],
  multiagent: [
    'agents' => ['agent_011CZkYqphY8vELVzwCUpqiQ', ['type' => 'self']],
    'type' => 'coordinator',
  ],
  skills: [['skillID' => 'xlsx', 'type' => 'anthropic', 'version' => '1']],
  system: 'You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user\'s task end to end.',
  tools: [
    [
      'type' => 'agent_toolset_20260401',
      'configs' => [
        [
          'name' => 'bash',
          'enabled' => true,
          'permissionPolicy' => ['type' => 'always_allow'],
          'type' => 'bash',
        ],
      ],
      'defaultConfig' => [
        'enabled' => true, 'permissionPolicy' => ['type' => 'always_allow']
      ],
    ],
  ],
  betas: [AnthropicBeta::MESSAGE_BATCHES_2024_09_24],
  workspaceID: 'wrkspc_011CZkZaBF1tNoB5wlCeusgy',
);

var_dump($betaManagedAgentsAgent);
Returns Examples
Response 200
{
  "id": "agent_011CZkYpogX7uDKUyvBTophP",
  "archived_at": null,
  "created_at": "2026-03-15T10:00:00Z",
  "description": "A general-purpose starter agent.",
  "execution_identity": {
    "type": "service_account"
  },
  "mcp_servers": [
    {
      "name": "example-mcp",
      "type": "url",
      "url": "https://example-server.modelcontextprotocol.io/sse"
    }
  ],
  "metadata": {
    "foo": "bar"
  },
  "model": {
    "id": "claude-opus-5-5",
    "effort": {
      "type": "low"
    },
    "inference_geo": "inference_geo",
    "speed": "standard"
  },
  "multiagent": {
    "advisor": {
      "type": "disabled"
    },
    "subagents": {
      "inline_agents": {
        "type": "enabled"
      },
      "predefined_agents": [
        {
          "id": "agent_011CZkYqphY8vELVzwCUpqiQ",
          "type": "agent",
          "version": 1
        }
      ],
      "type": "enabled"
    },
    "type": "multiagent_20261001",
    "workflows": {
      "inline_agents": {
        "type": "enabled"
      },
      "predefined_agents": [
        {
          "id": "agent_011CZkYqphY8vELVzwCUpqiQ",
          "type": "agent",
          "version": 1
        }
      ],
      "type": "enabled"
    }
  },
  "name": "My First Agent",
  "skills": [
    {
      "skill_id": "xlsx",
      "type": "anthropic",
      "version": "1"
    },
    {
      "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx",
      "type": "custom",
      "version": "2"
    }
  ],
  "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.",
  "tools": [
    {
      "configs": [
        {
          "enabled": true,
          "name": "bash",
          "permission_policy": {
            "type": "always_allow"
          },
          "type": "bash"
        }
      ],
      "default_config": {
        "enabled": true,
        "permission_policy": {
          "type": "always_ask"
        }
      },
      "type": "agent_toolset_20260401"
    }
  ],
  "type": "agent",
  "updated_at": "2026-03-15T10:00:00Z",
  "version": 1
}