Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

List Agents changed

api/beta/agents/list

Nearest release: v2.1.268, published under an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+368added
Lines−313removed
From line 1 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits9to this page, all time

The whole hunk

from line 1, old and new numbered
/
lines
from line 1
1---
2title: List Agents
3url: https://platform.claude.com/docs/en/api/beta/agents/list
4---
5 
16# List Agents
27 
38**GET** `/v1/agents`
from line 45
4045 
4146 - `string`
4247 
43 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
48 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
4449 
4550 - `"message-batches-2024-09-24"`
4651 
from line 93
8893 
8994 - `"user-profiles-2026-08-18"`
9095 
96 - `"user-profiles-2026-09-04"`
97 
9198 - `"advisor-tool-2026-03-01"`
9299 
93100 - `"managed-agents-2026-04-01"`
from line 137
130137 
131138 - `"mid-conversation-system-clear-at-2026-08-21"`
132139 
140- `"anthropic-workspace-id": optional string`
141 
133142## Returns
134143 
135144- `data: array of BetaManagedAgentsAgent`
from line 145
136145 
137146 List of agents.
138147 
148 - `type: "agent"`
149 
139150 - `id: string`
140151 
141152 - `archived_at: string or null`
from line 165
154165 
155166 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
156167 
157 - `name: string`
158 
159168 - `type: "url"`
160169 
170 - `name: string`
171 
161172 - `url: string`
162173 
163174 - `metadata: map[string]`
from line 297
286297 
287298 Resolved coordinator topology with a concrete agent roster.
288299 
300 - `type: "coordinator"`
301 
289302 - `agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor`
290303 
291304 Agents the coordinator may spawn as session threads, each resolved to a specific version.
from line 307
294307 
295308 A resolved agent reference with a concrete version.
296309 
297 - `id: string`
298 
299310 - `type: "agent"`
300311 
312 - `id: string`
313 
301314 - `version: number`
302315 
303316 format: int32
from line 319
306319 
307320 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
308321 
322 - `type: "advisor"`
323 
309324 - `model: string`
310325 
311326 The advisor model id.
312327 
313 - `type: "advisor"`
314 
315 - `type: "coordinator"`
316 
317328 - `name: string`
318329 
319330 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`
from line 333
322333 
323334 A resolved Anthropic-managed skill.
324335 
325 - `skill_id: string`
326 
327336 - `type: "anthropic"`
328337 
338 - `skill_id: string`
339 
329340 - `version: string`
330341 
331342 - `BetaManagedAgentsCustomSkill object`
from line 343
332343 
333344 A resolved user-created custom skill.
334345 
335 - `skill_id: string`
336 
337346 - `type: "custom"`
338347 
348 - `skill_id: string`
349 
339350 - `version: string`
340351 
341352 - `system: string or null`
from line 355
344355 
345356 - `BetaManagedAgentsAgentToolset20260401 object`
346357 
358 - `type: "agent_toolset_20260401"`
359 
347360 - `configs: array of BetaManagedAgentsAgentToolConfig`
348361 
349362 - `BetaManagedAgentsBashToolConfig object`
from line 363
350363 
351364 Configuration for the bash tool.
352365 
366 - `type: "bash"`
367 
353368 - `enabled: boolean`
354369 
355370 - `name: "bash"`
356371 
357 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
372 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
358373 
359374 Permission policy for tool execution.
360375 
from line 385
370385 
371386 - `type: "always_ask"`
372387 
373 - `type: "bash"`
388 - `BetaManagedAgentsAutoPolicy object`
374389 
390 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.
391 
392 - `type: "auto"`
393 
375394 - `BetaManagedAgentsEditToolConfig object`
376395 
377396 Configuration for the edit tool.
378397 
398 - `type: "edit"`
399 
379400 - `enabled: boolean`
380401 
381402 - `name: "edit"`
382403 
383 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
404 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
384405 
385406 Permission policy for tool execution.
386407 
from line 413
392413 
393414 Tool calls require user confirmation before execution.
394415 
395 - `type: "edit"`
416 - `BetaManagedAgentsAutoPolicy object`
396417 
418 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.
419 
397420 - `BetaManagedAgentsReadToolConfig object`
398421 
399422 Configuration for the read tool.
400423 
424 - `type: "read"`
425 
401426 - `enabled: boolean`
402427 
403428 - `name: "read"`
404429 
405 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
430 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
406431 
407432 Permission policy for tool execution.
408433 
from line 439
414439 
415440 Tool calls require user confirmation before execution.
416441 
417 - `type: "read"`
442 - `BetaManagedAgentsAutoPolicy object`
418443 
444 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.
445 
419446 - `BetaManagedAgentsWriteToolConfig object`
420447 
421448 Configuration for the write tool.
422449 
450 - `type: "write"`
451 
423452 - `enabled: boolean`
424453 
425454 - `name: "write"`
426455 
427 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
456 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
428457 
429458 Permission policy for tool execution.
430459 
from line 465
436465 
437466 Tool calls require user confirmation before execution.
438467 
439 - `type: "write"`
468 - `BetaManagedAgentsAutoPolicy object`
440469 
470 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.
471 
441472 - `BetaManagedAgentsGlobToolConfig object`
442473 
443474 Configuration for the glob tool.
444475 
476 - `type: "glob"`
477 
445478 - `enabled: boolean`
446479 
447480 - `name: "glob"`
448481 
449 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
482 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
450483 
451484 Permission policy for tool execution.
452485 
from line 491
458491 
459492 Tool calls require user confirmation before execution.
460493 
461 - `type: "glob"`
494 - `BetaManagedAgentsAutoPolicy object`
462495 
496 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.
497 
463498 - `BetaManagedAgentsGrepToolConfig object`
464499 
465500 Configuration for the grep tool.
466501 
502 - `type: "grep"`
503 
467504 - `enabled: boolean`
468505 
469506 - `name: "grep"`
470507 
471 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
508 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
472509 
473510 Permission policy for tool execution.
474511 
from line 517
480517 
481518 Tool calls require user confirmation before execution.
482519 
483 - `type: "grep"`
520 - `BetaManagedAgentsAutoPolicy object`
484521 
522 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.
523 
485524 - `BetaManagedAgentsWebFetchToolConfig object`
486525 
487526 Configuration for the web_fetch tool.
488527 
528 - `type: "web_fetch"`
529 
489530 - `enabled: boolean`
490531 
491532 - `name: "web_fetch"`
492533 
493 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
534 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
494535 
495536 Permission policy for tool execution.
496537 
from line 543
502543 
503544 Tool calls require user confirmation before execution.
504545 
505 - `type: "web_fetch"`
546 - `BetaManagedAgentsAutoPolicy object`
506547 
548 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.
549 
507550 - `allowed_domains: optional array of string`
508551 
509552 - `blocked_domains: optional array of string`
from line 559
516559 
517560 Configuration for the web_search tool.
518561 
562 - `type: "web_search"`
563 
519564 - `enabled: boolean`
520565 
521566 - `name: "web_search"`
522567 
523 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
568 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
524569 
525570 Permission policy for tool execution.
526571 
from line 577
532577 
533578 Tool calls require user confirmation before execution.
534579 
535 - `type: "web_search"`
580 - `BetaManagedAgentsAutoPolicy object`
536581 
582 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.
583 
537584 - `allowed_domains: optional array of string`
538585 
539586 - `blocked_domains: optional array of string`
from line 621
574621 
575622 - `enabled: boolean`
576623 
577 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
624 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
578625 
579626 Permission policy for tool execution.
580627 
from line 633
586633 
587634 Tool calls require user confirmation before execution.
588635 
589 - `type: "agent_toolset_20260401"`
636 - `BetaManagedAgentsAutoPolicy object`
590637 
638 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.
639 
591640 - `BetaManagedAgentsMCPToolset object`
592641 
642 - `type: "mcp_toolset"`
643 
593644 - `configs: array of BetaManagedAgentsMCPToolConfig`
594645 
595646 - `enabled: boolean`
from line 647
596647 
597648 - `name: string`
598649 
599 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
650 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
600651 
601652 Permission policy for tool execution.
602653 
from line 659
608659 
609660 Tool calls require user confirmation before execution.
610661 
662 - `BetaManagedAgentsAutoPolicy object`
663 
664 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.
665 
611666 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`
612667 
613668 Resolved default configuration for all tools from an MCP server.
from line 669
614669 
615670 - `enabled: boolean`
616671 
617 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy`
672 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`
618673 
619674 Permission policy for tool execution.
620675 
from line 681
626681 
627682 Tool calls require user confirmation before execution.
628683 
629 - `mcp_server_name: string`
684 - `BetaManagedAgentsAutoPolicy object`
630685 
631 - `type: "mcp_toolset"`
686 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.
632687 
688 - `mcp_server_name: string`
689 
633690 - `BetaManagedAgentsCustomTool object`
634691 
635692 A custom tool as returned in API responses.
636693 
694 - `type: "custom"`
695 
637696 - `description: string`
638697 
639698 - `input_schema: BetaManagedAgentsCustomToolInputSchema`
from line 706
647706 - `required: optional array of string or null`
648707 
649708 - `name: string`
650 
651 - `type: "custom"`
652 
653 - `type: "agent"`
654709 
655710 - `updated_at: string`
656711