## Create Agent `BetaManagedAgentsAgent beta().agents().create(AgentCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **post** `/v1/agents` Create Agent ### Parameters - `AgentCreateParams params` - `Optional> betas` Optional header to specify the beta version(s) you want to use. - `MESSAGE_BATCHES_2024_09_24("message-batches-2024-09-24")` - `PROMPT_CACHING_2024_07_31("prompt-caching-2024-07-31")` - `COMPUTER_USE_2024_10_22("computer-use-2024-10-22")` - `COMPUTER_USE_2025_01_24("computer-use-2025-01-24")` - `PDFS_2024_09_25("pdfs-2024-09-25")` - `TOKEN_COUNTING_2024_11_01("token-counting-2024-11-01")` - `TOKEN_EFFICIENT_TOOLS_2025_02_19("token-efficient-tools-2025-02-19")` - `OUTPUT_128K_2025_02_19("output-128k-2025-02-19")` - `FILES_API_2025_04_14("files-api-2025-04-14")` - `MCP_CLIENT_2025_04_04("mcp-client-2025-04-04")` - `MCP_CLIENT_2025_11_20("mcp-client-2025-11-20")` - `DEV_FULL_THINKING_2025_05_14("dev-full-thinking-2025-05-14")` - `INTERLEAVED_THINKING_2025_05_14("interleaved-thinking-2025-05-14")` - `CODE_EXECUTION_2025_05_22("code-execution-2025-05-22")` - `EXTENDED_CACHE_TTL_2025_04_11("extended-cache-ttl-2025-04-11")` - `CONTEXT_1M_2025_08_07("context-1m-2025-08-07")` - `CONTEXT_MANAGEMENT_2025_06_27("context-management-2025-06-27")` - `MODEL_CONTEXT_WINDOW_EXCEEDED_2025_08_26("model-context-window-exceeded-2025-08-26")` - `SKILLS_2025_10_02("skills-2025-10-02")` - `FAST_MODE_2026_02_01("fast-mode-2026-02-01")` - `OUTPUT_300K_2026_03_24("output-300k-2026-03-24")` - `USER_PROFILES_2026_03_24("user-profiles-2026-03-24")` - `ADVISOR_TOOL_2026_03_01("advisor-tool-2026-03-01")` - `MANAGED_AGENTS_2026_04_01("managed-agents-2026-04-01")` - `CACHE_DIAGNOSIS_2026_04_07("cache-diagnosis-2026-04-07")` - `THINKING_TOKEN_COUNT_2026_05_13("thinking-token-count-2026-05-13")` - `Model model` Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison), e.g. `claude-opus-4-6`, or a `model_config` object for additional configuration control - `enum BetaManagedAgentsModel:` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `CLAUDE_OPUS_4_8("claude-opus-4-8")` Frontier intelligence for long-running agents and coding - `CLAUDE_OPUS_4_7("claude-opus-4-7")` Frontier intelligence for long-running agents and coding - `CLAUDE_OPUS_4_6("claude-opus-4-6")` Most intelligent model for building agents and coding - `CLAUDE_SONNET_4_6("claude-sonnet-4-6")` Best combination of speed and intelligence - `CLAUDE_HAIKU_4_5("claude-haiku-4-5")` Fastest model with near-frontier intelligence - `CLAUDE_HAIKU_4_5_20251001("claude-haiku-4-5-20251001")` Fastest model with near-frontier intelligence - `CLAUDE_OPUS_4_5("claude-opus-4-5")` Premium model combining maximum intelligence with practical performance - `CLAUDE_OPUS_4_5_20251101("claude-opus-4-5-20251101")` Premium model combining maximum intelligence with practical performance - `CLAUDE_SONNET_4_5("claude-sonnet-4-5")` High-performance model for agents and coding - `CLAUDE_SONNET_4_5_20250929("claude-sonnet-4-5-20250929")` High-performance model for agents and coding - `class BetaManagedAgentsModelConfigParams:` An object that defines additional configuration control over model use - `BetaManagedAgentsModel id` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `Optional speed` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. - `STANDARD("standard")` - `FAST("fast")` - `String name` Human-readable name for the agent. 1-256 characters. - `Optional description` Description of what the agent does. Up to 2048 characters. - `Optional> mcpServers` MCP servers this agent connects to. Maximum 20. Names must be unique within the array. - `String name` Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. - `Type type` - `URL("url")` - `String url` Endpoint URL for the MCP server. - `Optional metadata` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `Optional multiagent` A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the `agents` roster. - `Optional> skills` Skills available to the agent. Maximum 20. - `class BetaManagedAgentsAnthropicSkillParams:` An Anthropic-managed skill. - `String skillId` Identifier of the Anthropic skill (e.g., "xlsx"). - `Type type` - `ANTHROPIC("anthropic")` - `Optional version` Version to pin. Defaults to latest if omitted. - `class BetaManagedAgentsCustomSkillParams:` A user-created custom skill. - `String skillId` Tagged ID of the custom skill (e.g., "skill_01XJ5..."). - `Type type` - `CUSTOM("custom")` - `Optional version` Version to pin. Defaults to latest if omitted. - `Optional system` System prompt for the agent. Up to 100,000 characters. - `Optional> tools` Tool configurations available to the agent. Maximum of 128 tools across all toolsets allowed. - `class BetaManagedAgentsAgentToolset20260401Params:` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `Type type` - `AGENT_TOOLSET_20260401("agent_toolset_20260401")` - `Optional> configs` Per-tool configuration overrides. - `Name name` Built-in agent tool identifier. - `BASH("bash")` - `EDIT("edit")` - `READ("read")` - `WRITE("write")` - `GLOB("glob")` - `GREP("grep")` - `WEB_FETCH("web_fetch")` - `WEB_SEARCH("web_search")` - `Optional enabled` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `Optional permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `Type type` - `ALWAYS_ALLOW("always_allow")` - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `Type type` - `ALWAYS_ASK("always_ask")` - `Optional defaultConfig` Default configuration for all tools in a toolset. - `Optional enabled` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `Optional permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `class BetaManagedAgentsMcpToolsetParams:` Configuration for tools from an MCP server defined in `mcp_servers`. - `String mcpServerName` Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. - `Type type` - `MCP_TOOLSET("mcp_toolset")` - `Optional> configs` Per-tool configuration overrides. - `String name` Name of the MCP tool to configure. 1-128 characters. - `Optional enabled` Whether this tool is enabled. Overrides the `default_config` setting. - `Optional permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `Optional defaultConfig` Default configuration for all tools from an MCP server. - `Optional enabled` Whether tools are enabled by default. Defaults to true if not specified. - `Optional permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `class BetaManagedAgentsCustomToolParams:` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event. - `String description` Description of what the tool does, shown to the agent to help it decide when to use the tool. 1-1024 characters. - `BetaManagedAgentsCustomToolInputSchema inputSchema` JSON Schema for custom tool input parameters. - `Optional properties` JSON Schema properties defining the tool's input parameters. - `Optional> required` List of required property names. - `Optional type` Must be 'object' for tool input schemas. - `OBJECT("object")` - `String name` Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. - `Type type` - `CUSTOM("custom")` ### Returns - `class BetaManagedAgentsAgent:` A Managed Agents `agent`. - `String id` - `Optional archivedAt` A timestamp in RFC 3339 format - `LocalDateTime createdAt` A timestamp in RFC 3339 format - `Optional description` - `List mcpServers` - `String name` - `Type type` - `URL("url")` - `String url` - `Metadata metadata` - `BetaManagedAgentsModelConfig model` Model identifier and configuration. - `BetaManagedAgentsModel id` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `CLAUDE_OPUS_4_8("claude-opus-4-8")` Frontier intelligence for long-running agents and coding - `CLAUDE_OPUS_4_7("claude-opus-4-7")` Frontier intelligence for long-running agents and coding - `CLAUDE_OPUS_4_6("claude-opus-4-6")` Most intelligent model for building agents and coding - `CLAUDE_SONNET_4_6("claude-sonnet-4-6")` Best combination of speed and intelligence - `CLAUDE_HAIKU_4_5("claude-haiku-4-5")` Fastest model with near-frontier intelligence - `CLAUDE_HAIKU_4_5_20251001("claude-haiku-4-5-20251001")` Fastest model with near-frontier intelligence - `CLAUDE_OPUS_4_5("claude-opus-4-5")` Premium model combining maximum intelligence with practical performance - `CLAUDE_OPUS_4_5_20251101("claude-opus-4-5-20251101")` Premium model combining maximum intelligence with practical performance - `CLAUDE_SONNET_4_5("claude-sonnet-4-5")` High-performance model for agents and coding - `CLAUDE_SONNET_4_5_20250929("claude-sonnet-4-5-20250929")` High-performance model for agents and coding - `Optional speed` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. - `STANDARD("standard")` - `FAST("fast")` - `Optional multiagent` Resolved coordinator topology with a concrete agent roster. - `List agents` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `String id` - `Type type` - `AGENT("agent")` - `long version` - `Type type` - `COORDINATOR("coordinator")` - `String name` - `List skills` - `class BetaManagedAgentsAnthropicSkill:` A resolved Anthropic-managed skill. - `String skillId` - `Type type` - `ANTHROPIC("anthropic")` - `String version` - `class BetaManagedAgentsCustomSkill:` A resolved user-created custom skill. - `String skillId` - `Type type` - `CUSTOM("custom")` - `String version` - `Optional system` - `List tools` - `class BetaManagedAgentsAgentToolset20260401:` - `List configs` - `boolean enabled` - `Name name` Built-in agent tool identifier. - `BASH("bash")` - `EDIT("edit")` - `READ("read")` - `WRITE("write")` - `GLOB("glob")` - `GREP("grep")` - `WEB_FETCH("web_fetch")` - `WEB_SEARCH("web_search")` - `PermissionPolicy permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `Type type` - `ALWAYS_ALLOW("always_allow")` - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `Type type` - `ALWAYS_ASK("always_ask")` - `BetaManagedAgentsAgentToolsetDefaultConfig defaultConfig` Resolved default configuration for agent tools. - `boolean enabled` - `PermissionPolicy permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `Type type` - `AGENT_TOOLSET_20260401("agent_toolset_20260401")` - `class BetaManagedAgentsMcpToolset:` - `List configs` - `boolean enabled` - `String name` - `PermissionPolicy permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `BetaManagedAgentsMcpToolsetDefaultConfig defaultConfig` Resolved default configuration for all tools from an MCP server. - `boolean enabled` - `PermissionPolicy permissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy:` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy:` Tool calls require user confirmation before execution. - `String mcpServerName` - `Type type` - `MCP_TOOLSET("mcp_toolset")` - `class BetaManagedAgentsCustomTool:` A custom tool as returned in API responses. - `String description` - `BetaManagedAgentsCustomToolInputSchema inputSchema` JSON Schema for custom tool input parameters. - `Optional properties` JSON Schema properties defining the tool's input parameters. - `Optional> required` List of required property names. - `Optional type` Must be 'object' for tool input schemas. - `OBJECT("object")` - `String name` - `Type type` - `CUSTOM("custom")` - `Type type` - `AGENT("agent")` - `LocalDateTime updatedAt` A timestamp in RFC 3339 format - `long version` The agent's current version. Starts at 1 and increments when the agent is modified. ### Example ```java package com.anthropic.example; import com.anthropic.client.AnthropicClient; import com.anthropic.client.okhttp.AnthropicOkHttpClient; import com.anthropic.models.beta.agents.AgentCreateParams; import com.anthropic.models.beta.agents.BetaManagedAgentsAgent; import com.anthropic.models.beta.agents.BetaManagedAgentsModel; public final class Main { private Main() {} public static void main(String[] args) { AnthropicClient client = AnthropicOkHttpClient.fromEnv(); AgentCreateParams params = AgentCreateParams.builder() .model(BetaManagedAgentsModel.CLAUDE_SONNET_4_6) .name("My First Agent") .build(); BetaManagedAgentsAgent betaManagedAgentsAgent = client.beta().agents().create(params); } } ``` #### Response ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-sonnet-4-6", "speed": "standard" }, "multiagent": { "agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "coordinator" }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTlx", "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" } } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ```