The whole hunk
from line 1, old and new numbered
/
lines
from line 1
1---
2title: Get Agent
3url: https://platform.claude.com/docs/en/api/beta/agents/retrieve
4---
5
16# Get Agent
27
38**GET** `/v1/agents/{agent_id}`
from line 29
2429
2530 - `string`
2631
27 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
32 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
2833
2934 - `"message-batches-2024-09-24"`
3035
from line 77
7277
7378 - `"user-profiles-2026-08-18"`
7479
80 - `"user-profiles-2026-09-04"`
81
7582 - `"advisor-tool-2026-03-01"`
7683
7784 - `"managed-agents-2026-04-01"`
from line 121
114121
115122 - `"mid-conversation-system-clear-at-2026-08-21"`
116123
124- `"anthropic-workspace-id": optional string`
125
117126## Returns
118127
119128- `BetaManagedAgentsAgent object`
from line 129
120129
121130 A Managed Agents `agent`.
122131
132 - `type: "agent"`
133
123134 - `id: string`
124135
125136 - `archived_at: string or null`
from line 149
138149
139150 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
140151
141 - `name: string`
142
143152 - `type: "url"`
144153
154 - `name: string`
155
145156 - `url: string`
146157
147158 - `metadata: map[string]`
from line 281
270281
271282 Resolved coordinator topology with a concrete agent roster.
272283
284 - `type: "coordinator"`
285
273286 - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor`
274287
275288 Agents the coordinator may spawn as session threads, each resolved to a specific version.
from line 291
278291
279292 A resolved agent reference with a concrete version.
280293
281 - `id: string`
282
283294 - `type: "agent"`
284295
296 - `id: string`
297
285298 - `version: number`
286299
287300 format: int32
from line 303
290303
291304 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
292305
306 - `type: "advisor"`
307
293308 - `model: string`
294309
295310 The advisor model id.
296311
297 - `type: "advisor"`
298
299 - `type: "coordinator"`
300
301312 - `name: string`
302313
303314 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
from line 317
306317
307318 A resolved Anthropic-managed skill.
308319
309 - `skill_id: string`
310
311320 - `type: "anthropic"`
312321
322 - `skill_id: string`
323
313324 - `version: string`
314325
315326 - `BetaManagedAgentsCustomSkill object`
from line 327
316327
317328 A resolved user-created custom skill.
318329
319 - `skill_id: string`
320
321330 - `type: "custom"`
322331
332 - `skill_id: string`
333
323334 - `version: string`
324335
325336 - `system: string or null`
from line 339
328339
329340 - `BetaManagedAgentsAgentToolset20260401 object`
330341
342 - `type: "agent_toolset_20260401"`
343
331344 - `configs: array of BetaManagedAgentsAgentToolConfig`
332345
333346 - `BetaManagedAgentsBashToolConfig object`
from line 347
334347
335348 Configuration for the bash tool.
336349
350 - `type: "bash"`
351
337352 - `enabled: boolean`
338353
339354 - `name: "bash"`
340355
341 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
356 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
342357
343358 Permission policy for tool execution.
344359
from line 369
354369
355370 - `type: "always_ask"`
356371
357 - `type: "bash"`
372 - `BetaManagedAgentsAutoPolicy object`
358373
374 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.
375
376 - `type: "auto"`
377
359378 - `BetaManagedAgentsEditToolConfig object`
360379
361380 Configuration for the edit tool.
362381
382 - `type: "edit"`
383
363384 - `enabled: boolean`
364385
365386 - `name: "edit"`
366387
367 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
388 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
368389
369390 Permission policy for tool execution.
370391
from line 397
376397
377398 Tool calls require user confirmation before execution.
378399
379 - `type: "edit"`
400 - `BetaManagedAgentsAutoPolicy object`
380401
402 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.
403
381404 - `BetaManagedAgentsReadToolConfig object`
382405
383406 Configuration for the read tool.
384407
408 - `type: "read"`
409
385410 - `enabled: boolean`
386411
387412 - `name: "read"`
388413
389 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
414 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
390415
391416 Permission policy for tool execution.
392417
from line 423
398423
399424 Tool calls require user confirmation before execution.
400425
401 - `type: "read"`
426 - `BetaManagedAgentsAutoPolicy object`
402427
428 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.
429
403430 - `BetaManagedAgentsWriteToolConfig object`
404431
405432 Configuration for the write tool.
406433
434 - `type: "write"`
435
407436 - `enabled: boolean`
408437
409438 - `name: "write"`
410439
411 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
440 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
412441
413442 Permission policy for tool execution.
414443
from line 449
420449
421450 Tool calls require user confirmation before execution.
422451
423 - `type: "write"`
452 - `BetaManagedAgentsAutoPolicy object`
424453
454 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.
455
425456 - `BetaManagedAgentsGlobToolConfig object`
426457
427458 Configuration for the glob tool.
428459
460 - `type: "glob"`
461
429462 - `enabled: boolean`
430463
431464 - `name: "glob"`
432465
433 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
466 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
434467
435468 Permission policy for tool execution.
436469
from line 475
442475
443476 Tool calls require user confirmation before execution.
444477
445 - `type: "glob"`
478 - `BetaManagedAgentsAutoPolicy object`
446479
480 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.
481
447482 - `BetaManagedAgentsGrepToolConfig object`
448483
449484 Configuration for the grep tool.
450485
486 - `type: "grep"`
487
451488 - `enabled: boolean`
452489
453490 - `name: "grep"`
454491
455 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
492 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
456493
457494 Permission policy for tool execution.
458495
from line 501
464501
465502 Tool calls require user confirmation before execution.
466503
467 - `type: "grep"`
504 - `BetaManagedAgentsAutoPolicy object`
468505
506 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.
507
469508 - `BetaManagedAgentsWebFetchToolConfig object`
470509
471510 Configuration for the web_fetch tool.
472511
512 - `type: "web_fetch"`
513
473514 - `enabled: boolean`
474515
475516 - `name: "web_fetch"`
476517
477 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
518 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
478519
479520 Permission policy for tool execution.
480521
from line 527
486527
487528 Tool calls require user confirmation before execution.
488529
489 - `type: "web_fetch"`
530 - `BetaManagedAgentsAutoPolicy object`
490531
532 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.
533
491534 - `allowed_domains: optional array of string`
492535
493536 - `blocked_domains: optional array of string`
from line 543
500543
501544 Configuration for the web_search tool.
502545
546 - `type: "web_search"`
547
503548 - `enabled: boolean`
504549
505550 - `name: "web_search"`
506551
507 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
552 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
508553
509554 Permission policy for tool execution.
510555
from line 561
516561
517562 Tool calls require user confirmation before execution.
518563
519 - `type: "web_search"`
564 - `BetaManagedAgentsAutoPolicy object`
520565
566 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.
567
521568 - `allowed_domains: optional array of string`
522569
523570 - `blocked_domains: optional array of string`
from line 605
558605
559606 - `enabled: boolean`
560607
561 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
608 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
562609
563610 Permission policy for tool execution.
564611
from line 617
570617
571618 Tool calls require user confirmation before execution.
572619
573 - `type: "agent_toolset_20260401"`
620 - `BetaManagedAgentsAutoPolicy object`
574621
622 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.
623
575624 - `BetaManagedAgentsMCPToolset object`
576625
626 - `type: "mcp_toolset"`
627
577628 - `configs: array of BetaManagedAgentsMCPToolConfig`
578629
579630 - `enabled: boolean`
from line 631
580631
581632 - `name: string`
582633
583 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
634 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
584635
585636 Permission policy for tool execution.
586637
from line 643
592643
593644 Tool calls require user confirmation before execution.
594645
646 - `BetaManagedAgentsAutoPolicy object`
647
648 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.
649
595650 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`
596651
597652 Resolved default configuration for all tools from an MCP server.
from line 653
598653
599654 - `enabled: boolean`
600655
601 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
656 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
602657
603658 Permission policy for tool execution.
604659
from line 665
610665
611666 Tool calls require user confirmation before execution.
612667
613 - `mcp_server_name: string`
668 - `BetaManagedAgentsAutoPolicy object`
614669
615 - `type: "mcp_toolset"`
670 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.
616671
672 - `mcp_server_name: string`
673
617674 - `BetaManagedAgentsCustomTool object`
618675
619676 A custom tool as returned in API responses.
620677
678 - `type: "custom"`
679
621680 - `description: string`
622681
623682 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
from line 690
631690 - `required: optional array of string or null`
632691
633692 - `name: string`
634
635 - `type: "custom"`
636
637 - `type: "agent"`
638693
639694 - `updated_at: string`
640695