Repository Public
1---2title: Archive Agent3url: https://platform.claude.com/docs/en/api/beta/agents/archive4---56# Archive Agent78**POST** `/v1/agents/{agent_id}/archive`910Archive Agent1112## Path parameters1314- `agent_id: string`1516## Headers1718- `"anthropic-beta": optional array of AnthropicBeta`1920 Optional header to specify the beta version(s) you want to use.2122 - `string`2324 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`2526 - `"message-batches-2024-09-24"`2728 - `"prompt-caching-2024-07-31"`2930 - `"computer-use-2024-10-22"`3132 - `"computer-use-2025-01-24"`3334 - `"pdfs-2024-09-25"`3536 - `"token-counting-2024-11-01"`3738 - `"token-efficient-tools-2025-02-19"`3940 - `"output-128k-2025-02-19"`4142 - `"files-api-2025-04-14"`4344 - `"mcp-client-2025-04-04"`4546 - `"mcp-client-2025-11-20"`4748 - `"dev-full-thinking-2025-05-14"`4950 - `"interleaved-thinking-2025-05-14"`5152 - `"code-execution-2025-05-22"`5354 - `"extended-cache-ttl-2025-04-11"`5556 - `"context-1m-2025-08-07"`5758 - `"context-management-2025-06-27"`5960 - `"model-context-window-exceeded-2025-08-26"`6162 - `"skills-2025-10-02"`6364 - `"fast-mode-2026-02-01"`6566 - `"output-300k-2026-03-24"`6768 - `"user-profiles-2026-03-24"`6970 - `"user-profiles-2026-08-18"`7172 - `"user-profiles-2026-09-04"`7374 - `"advisor-tool-2026-03-01"`7576 - `"managed-agents-2026-04-01"`7778 - `"cache-diagnosis-2026-04-07"`7980 - `"dreaming-2026-04-21"`8182 - `"thinking-token-count-2026-05-13"`8384 - `"server-side-fallback-2026-06-01"`8586 - `"server-side-fallback-2026-07-01"`8788 - `"fallback-credit-2026-06-01"`8990 - `"fallback-credit-2026-07-01"`9192 - `"agent-memory-2026-07-22"`9394 - `"mid-conversation-tool-changes-2026-07-01"`9596 - `"compact-2026-01-12"`9798 - `"computer-use-2025-11-24"`99100 - `"mcp-tunnels-2026-06-22"`101102 - `"structured-outputs-2025-11-13"`103104 - `"task-budgets-2026-03-13"`105106 - `"thinking-display-updates-2026-08-18"`107108 - `"ce-user-management-2026-07-13"`109110 - `"mid-conversation-output-config-2026-07-01"`111112 - `"thinking-binding-controls-2026-08-01"`113114 - `"mid-conversation-system-clear-at-2026-08-21"`115116 - `"compact-2026-09-04"`117118- `"anthropic-workspace-id": optional string`119120## Returns121122- `BetaManagedAgentsAgent object`123124 A Managed Agents `agent`.125126 - `type: "agent"`127128 - `id: string`129130 - `archived_at: string or null`131132 A timestamp in RFC 3339 format133134 format: date-time135136 - `created_at: string`137138 A timestamp in RFC 3339 format139140 format: date-time141142 - `description: string or null`143144 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`145146 - `type: "url"`147148 - `name: string`149150 - `url: string`151152 - `metadata: map[string]`153154 - `model: BetaManagedAgentsModelConfig`155156 Model identifier and configuration.157158 - `id: BetaManagedAgentsModel`159160 The model that will power your agent.161162 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.163164 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`165166 The model that will power your agent.167168 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.169170 - `"claude-fable-5-1"`171172 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows173174 - `"claude-sonnet-5"`175176 High-performance model for coding and agents177178 - `"claude-fable-5"`179180 Next generation of intelligence for the hardest knowledge work and coding problems181182 - `"claude-opus-5"`183184 Powerful intelligence for long-running agents and coding185186 - `"claude-opus-4-8"`187188 Powerful intelligence for long-running agents and coding189190 - `"claude-opus-4-7"`191192 Powerful intelligence for long-running agents and coding193194 - `"claude-opus-4-6"`195196 Powerful intelligence for long-running agents and coding197198 - `"claude-sonnet-4-6"`199200 Best combination of speed and intelligence201202 - `"claude-haiku-4-5"`203204 Fastest model with near-frontier intelligence205206 - `"claude-haiku-4-5-20251001"`207208 Fastest model with near-frontier intelligence209210 - `"claude-opus-4-5"`211212 Powerful intelligence for long-running agents and coding213214 - `"claude-opus-4-5-20251101"`215216 Powerful intelligence for long-running agents and coding217218 - `"claude-sonnet-4-5"`219220 High-performance model for agents and coding221222 - `"claude-sonnet-4-5-20250929"`223224 High-performance model for agents and coding225226 - `string`227228 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`229230 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.231232 - `BetaManagedAgentsEffortLow object`233234 Low effort. Favors latency over reasoning depth.235236 - `type: "low"`237238 - `BetaManagedAgentsEffortMedium object`239240 Medium effort. Balances latency and reasoning depth.241242 - `type: "medium"`243244 - `BetaManagedAgentsEffortHigh object`245246 High effort. Favors reasoning depth.247248 - `type: "high"`249250 - `BetaManagedAgentsEffortXhigh object`251252 Extra-high effort. Not all models accept this level.253254 - `type: "xhigh"`255256 - `BetaManagedAgentsEffortMax object`257258 Maximum effort. Favors reasoning depth over latency.259260 - `type: "max"`261262 - `inference_geo: optional string`263264 Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.265266 - `speed: optional "standard" or "fast"`267268 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.269270 - `"standard"`271272 - `"fast"`273274 - `multiagent: BetaManagedAgentsMultiagent or null`275276 Resolved coordinator topology with a concrete agent roster.277278 - `type: "coordinator"`279280 - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor`281282 Agents the coordinator may spawn as session threads, each resolved to a specific version.283284 - `BetaManagedAgentsAgentReference object`285286 A resolved agent reference with a concrete version.287288 - `type: "agent"`289290 - `id: string`291292 - `version: number`293294 format: int32295296 - `BetaManagedAgentsAdvisor object`297298 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.299300 - `type: "advisor"`301302 - `model: string`303304 The advisor model id.305306 - `name: string`307308 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`309310 - `BetaManagedAgentsAnthropicSkill object`311312 A resolved Anthropic-managed skill.313314 - `type: "anthropic"`315316 - `skill_id: string`317318 - `version: string`319320 - `BetaManagedAgentsCustomSkill object`321322 A resolved user-created custom skill.323324 - `type: "custom"`325326 - `skill_id: string`327328 - `version: string`329330 - `system: string or null`331332 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`333334 - `BetaManagedAgentsAgentToolset20260401 object`335336 - `type: "agent_toolset_20260401"`337338 - `configs: array of BetaManagedAgentsAgentToolConfig`339340 - `BetaManagedAgentsBashToolConfig object`341342 Configuration for the bash tool.343344 - `type: "bash"`345346 - `enabled: boolean`347348 - `name: "bash"`349350 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`351352 Permission policy for tool execution.353354 - `BetaManagedAgentsAlwaysAllowPolicy object`355356 Tool calls are automatically approved without user confirmation.357358 - `type: "always_allow"`359360 - `BetaManagedAgentsAlwaysAskPolicy object`361362 Tool calls require user confirmation before execution.363364 - `type: "always_ask"`365366 - `BetaManagedAgentsAutoPolicy object`367368 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.369370 - `type: "auto"`371372 - `BetaManagedAgentsEditToolConfig object`373374 Configuration for the edit tool.375376 - `type: "edit"`377378 - `enabled: boolean`379380 - `name: "edit"`381382 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`383384 Permission policy for tool execution.385386 - `BetaManagedAgentsAlwaysAllowPolicy object`387388 Tool calls are automatically approved without user confirmation.389390 - `BetaManagedAgentsAlwaysAskPolicy object`391392 Tool calls require user confirmation before execution.393394 - `BetaManagedAgentsAutoPolicy object`395396 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.397398 - `BetaManagedAgentsReadToolConfig object`399400 Configuration for the read tool.401402 - `type: "read"`403404 - `enabled: boolean`405406 - `name: "read"`407408 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`409410 Permission policy for tool execution.411412 - `BetaManagedAgentsAlwaysAllowPolicy object`413414 Tool calls are automatically approved without user confirmation.415416 - `BetaManagedAgentsAlwaysAskPolicy object`417418 Tool calls require user confirmation before execution.419420 - `BetaManagedAgentsAutoPolicy object`421422 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.423424 - `BetaManagedAgentsWriteToolConfig object`425426 Configuration for the write tool.427428 - `type: "write"`429430 - `enabled: boolean`431432 - `name: "write"`433434 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`435436 Permission policy for tool execution.437438 - `BetaManagedAgentsAlwaysAllowPolicy object`439440 Tool calls are automatically approved without user confirmation.441442 - `BetaManagedAgentsAlwaysAskPolicy object`443444 Tool calls require user confirmation before execution.445446 - `BetaManagedAgentsAutoPolicy object`447448 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.449450 - `BetaManagedAgentsGlobToolConfig object`451452 Configuration for the glob tool.453454 - `type: "glob"`455456 - `enabled: boolean`457458 - `name: "glob"`459460 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`461462 Permission policy for tool execution.463464 - `BetaManagedAgentsAlwaysAllowPolicy object`465466 Tool calls are automatically approved without user confirmation.467468 - `BetaManagedAgentsAlwaysAskPolicy object`469470 Tool calls require user confirmation before execution.471472 - `BetaManagedAgentsAutoPolicy object`473474 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.475476 - `BetaManagedAgentsGrepToolConfig object`477478 Configuration for the grep tool.479480 - `type: "grep"`481482 - `enabled: boolean`483484 - `name: "grep"`485486 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`487488 Permission policy for tool execution.489490 - `BetaManagedAgentsAlwaysAllowPolicy object`491492 Tool calls are automatically approved without user confirmation.493494 - `BetaManagedAgentsAlwaysAskPolicy object`495496 Tool calls require user confirmation before execution.497498 - `BetaManagedAgentsAutoPolicy object`499500 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.501502 - `BetaManagedAgentsWebFetchToolConfig object`503504 Configuration for the web_fetch tool.505506 - `type: "web_fetch"`507508 - `enabled: boolean`509510 - `name: "web_fetch"`511512 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`513514 Permission policy for tool execution.515516 - `BetaManagedAgentsAlwaysAllowPolicy object`517518 Tool calls are automatically approved without user confirmation.519520 - `BetaManagedAgentsAlwaysAskPolicy object`521522 Tool calls require user confirmation before execution.523524 - `BetaManagedAgentsAutoPolicy object`525526 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.527528 - `allowed_domains: optional array of string`529530 - `blocked_domains: optional array of string`531532 - `max_content_tokens: optional number or null`533534 format: int32535536 - `BetaManagedAgentsWebSearchToolConfig object`537538 Configuration for the web_search tool.539540 - `type: "web_search"`541542 - `enabled: boolean`543544 - `name: "web_search"`545546 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`547548 Permission policy for tool execution.549550 - `BetaManagedAgentsAlwaysAllowPolicy object`551552 Tool calls are automatically approved without user confirmation.553554 - `BetaManagedAgentsAlwaysAskPolicy object`555556 Tool calls require user confirmation before execution.557558 - `BetaManagedAgentsAutoPolicy object`559560 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.561562 - `allowed_domains: optional array of string`563564 - `blocked_domains: optional array of string`565566 - `user_location: optional BetaManagedAgentsUserLocation or null`567568 Approximate user location for search result localization.569570 - `type: "approximate"`571572 Location precision. Only "approximate" is supported.573574 - `city: optional string or null`575576 City name.577578 minLength: 1, maxLength: 255579580 - `country: optional string or null`581582 Two-letter ISO 3166-1 country code, uppercase.583584 - `region: optional string or null`585586 Region or state name.587588 minLength: 1, maxLength: 255589590 - `timezone: optional string or null`591592 IANA timezone identifier, e.g. "America/Los_Angeles".593594 minLength: 1, maxLength: 255595596 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig`597598 Resolved default configuration for agent tools.599600 - `enabled: boolean`601602 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`603604 Permission policy for tool execution.605606 - `BetaManagedAgentsAlwaysAllowPolicy object`607608 Tool calls are automatically approved without user confirmation.609610 - `BetaManagedAgentsAlwaysAskPolicy object`611612 Tool calls require user confirmation before execution.613614 - `BetaManagedAgentsAutoPolicy object`615616 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.617618 - `BetaManagedAgentsMCPToolset object`619620 - `type: "mcp_toolset"`621622 - `configs: array of BetaManagedAgentsMCPToolConfig`623624 - `enabled: boolean`625626 - `name: string`627628 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`629630 Permission policy for tool execution.631632 - `BetaManagedAgentsAlwaysAllowPolicy object`633634 Tool calls are automatically approved without user confirmation.635636 - `BetaManagedAgentsAlwaysAskPolicy object`637638 Tool calls require user confirmation before execution.639640 - `BetaManagedAgentsAutoPolicy object`641642 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.643644 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`645646 Resolved default configuration for all tools from an MCP server.647648 - `enabled: boolean`649650 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`651652 Permission policy for tool execution.653654 - `BetaManagedAgentsAlwaysAllowPolicy object`655656 Tool calls are automatically approved without user confirmation.657658 - `BetaManagedAgentsAlwaysAskPolicy object`659660 Tool calls require user confirmation before execution.661662 - `BetaManagedAgentsAutoPolicy object`663664 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.665666 - `mcp_server_name: string`667668 - `BetaManagedAgentsCustomTool object`669670 A custom tool as returned in API responses.671672 - `type: "custom"`673674 - `description: string`675676 - `input_schema: BetaManagedAgentsCustomToolInputSchema`677678 JSON Schema for custom tool input parameters.679680 - `type: "object"`681682 - `properties: optional map[unknown] or null`683684 - `required: optional array of string or null`685686 - `name: string`687688 - `updated_at: string`689690 A timestamp in RFC 3339 format691692 format: date-time693694 - `version: number`695696 The agent's current version. Starts at 1 and increments when the agent is modified.697698 format: int32699700## Example701702```bash703curl https://api.anthropic.com/v1/agents/$AGENT_ID/archive \704 -X POST \705 -H 'anthropic-version: 2023-06-01' \706 -H 'anthropic-beta: managed-agents-2026-04-01' \707 -H "X-Api-Key: $ANTHROPIC_API_KEY"708```709710### Response (200)711712```json713{714 "id": "agent_011CZkYpogX7uDKUyvBTophP",715 "archived_at": null,716 "created_at": "2026-03-15T10:00:00Z",717 "description": "A general-purpose starter agent.",718 "mcp_servers": [719 {720 "name": "example-mcp",721 "type": "url",722 "url": "https://example-server.modelcontextprotocol.io/sse"723 }724 ],725 "metadata": {726 "foo": "bar"727 },728 "model": {729 "id": "claude-opus-5",730 "effort": {731 "type": "low"732 },733 "inference_geo": "inference_geo",734 "speed": "standard"735 },736 "multiagent": {737 "agents": [738 {739 "id": "agent_011CZkYqphY8vELVzwCUpqiQ",740 "type": "agent",741 "version": 1742 }743 ],744 "type": "coordinator"745 },746 "name": "My First Agent",747 "skills": [748 {749 "skill_id": "xlsx",750 "type": "anthropic",751 "version": "1"752 },753 {754 "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTlx",755 "type": "custom",756 "version": "2"757 }758 ],759 "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.",760 "tools": [761 {762 "configs": [763 {764 "enabled": true,765 "name": "bash",766 "permission_policy": {767 "type": "always_allow"768 },769 "type": "bash"770 }771 ],772 "default_config": {773 "enabled": true,774 "permission_policy": {775 "type": "always_ask"776 }777 },778 "type": "agent_toolset_20260401"779 }780 ],781 "type": "agent",782 "updated_at": "2026-03-15T10:00:00Z",783 "version": 1784}785```786