One read of Claude Documentationclaude-docs-20261030T180712Z
71 pages moved out of 281 read.
Pages moved
71
significant first
Pages read
281
in this capture
Captured
18:07 UTC
Corpus hash
610846466448
sitemap-lastmod
What this read moved
26-50 of 71, page 2 of 3This capture is too large to show at once. Changes 26-50 of 71 are below, significant first; the rest are on the following screens.
third-party/claude-desktop/gateway Changed · +17 / -17 lines
from line 220
220220>
221221> * Use inferenceIdpAuthFlow together with inferenceIdpOidc once every desktop in the fleet is on a release that reads them. The original spelling will keep working; no end date has been set.
222222
223> **More detail**
223> [accordion] More detail
224224>
225225> * **`browser`:** register the redirect URI `http://127.0.0.1:<port>/callback` with your identity provider (for Entra, `http://127.0.0.1/callback`).
226226> * **`broker`:** uses Web Account Manager on Windows or Company Portal on macOS, and does not work on Linux. It can satisfy Conditional Access policies that require a compliant or managed device, or token protection.
from line 245
245245>
246246> * Use inferenceIdpOidc with inferenceCredentialKind: "external-idp" once every desktop in the fleet is on a release that reads them. The original spelling will keep working; no end date has been set.
247247
248> **More detail**
248> [accordion] More detail
249249>
250250> Used with `inferenceCredentialKind` set to `interactive`. Leave it unset for a gateway that runs its own sign-in and serves `<baseUrl>/.well-known/oauth-authorization-server`.
251251>
from line 253
253253>
254254> Register the redirect URI given under `inferenceGatewayOidcAuthFlow`.
255255
256> **Child attributes (11)**
256> [accordion] Child attributes (11)
257257>
258258> **clientId** `string` *required*
259259>
from line 277
277277>
278278> One of: `id_token` (default), `access_token`
279279>
280> > **More detail**
280> > [accordion] More detail
281281> >
282282> > An ID token's audience (`aud`) is `clientId`. An access token's audience must be your gateway or proxy.
283283> >
from line 287
287287>
288288> Space-separated scopes. Access-token mode needs the gateway or proxy API scope, and adds offline\_access unless Append offline\_access is off.
289289>
290> > **More detail**
290> > [accordion] More detail
291291> >
292292> > In ID-token mode, `offline_access` is not added to scopes that you set. Include it yourself, or users sign in again each time the token expires.
293293>
from line 295
295295>
296296> In access-token mode, add offline\_access to scopes so the identity provider returns a refresh token for silent refresh.
297297>
298> > **More detail**
298> > [accordion] More detail
299299> >
300300> > Turn off only if your authorization server rejects `offline_access` as an unknown scope. Then add the server’s own refresh-token scope to `scopes`.
301301>
from line 303
303303>
304304> Access-token audience of the gateway or proxy: an https URL or an AD FS relying-party identifier. Leave unset for Entra ID.
305305>
306> > **More detail**
306> > [accordion] More detail
307307> >
308308> > Use it only with `bearerTokenType` set to `access_token`, and only if your identity provider supports RFC 8707. Changing it signs users in again.
309309> >
from line 323
323323>
324324> Space-separated hostnames also accepted as the referrer of the sign-in callback, besides the authorization URL’s host.
325325>
326> > **More detail**
326> > [accordion] More detail
327327> >
328328> > If a callback is rejected for a referrer mismatch, the app log names the rejected host. Add that hostname here.
329329
from line 337
337337
338338One of: `browser`, `broker`
339339
340> **More detail**
340> [accordion] More detail
341341>
342342> * **`browser`:** register the redirect URI `http://127.0.0.1:<port>/callback` with your identity provider (for Entra, `http://127.0.0.1/callback`).
343343> * **`broker`:** uses Web Account Manager on Windows or Company Portal on macOS, and does not work on Linux. It can satisfy Conditional Access policies that require a compliant or managed device, or token protection.
from line 356
356356
357357**Identity provider (OIDC).** Your organization’s OpenID Connect identity provider. The user’s token is sent as the Bearer credential to the gateway or the Bedrock proxy.
358358
359> **More detail**
359> [accordion] More detail
360360>
361361> Used when `inferenceCredentialKind` is `external-idp`. Register the redirect URI given under `inferenceIdpAuthFlow` with your identity provider.
362362>
from line 364
364364>
365365> On Bedrock, set `inferenceBedrockBaseUrl` to a proxy that checks the token, because Amazon Bedrock itself does not accept it. Also list your models in `inferenceModels`.
366366
367> **Child attributes (11)**
367> [accordion] Child attributes (11)
368368>
369369> **clientId** `string` *required*
370370>
from line 388
388388>
389389> One of: `id_token` (default), `access_token`
390390>
391> > **More detail**
391> > [accordion] More detail
392392> >
393393> > An ID token's audience (`aud`) is `clientId`. An access token's audience must be your gateway or proxy.
394394> >
from line 398
398398>
399399> Space-separated scopes. Access-token mode needs the gateway or proxy API scope, and adds offline\_access unless Append offline\_access is off.
400400>
401> > **More detail**
401> > [accordion] More detail
402402> >
403403> > In ID-token mode, `offline_access` is not added to scopes that you set. Include it yourself, or users sign in again each time the token expires.
404404>
from line 406
406406>
407407> In access-token mode, add offline\_access to scopes so the identity provider returns a refresh token for silent refresh.
408408>
409> > **More detail**
409> > [accordion] More detail
410410> >
411411> > Turn off only if your authorization server rejects `offline_access` as an unknown scope. Then add the server’s own refresh-token scope to `scopes`.
412412>
from line 414
414414>
415415> Access-token audience of the gateway or proxy: an https URL or an AD FS relying-party identifier. Leave unset for Entra ID.
416416>
417> > **More detail**
417> > [accordion] More detail
418418> >
419419> > Use it only with `bearerTokenType` set to `access_token`, and only if your identity provider supports RFC 8707. Changing it signs users in again.
420420> >
from line 434
434434>
435435> Space-separated hostnames also accepted as the referrer of the sign-in callback, besides the authorization URL’s host.
436436>
437> > **More detail**
437> > [accordion] More detail
438438> >
439439> > If a callback is rejected for a referrer mismatch, the app log names the rejected host. Add that hostname here.
440440
from line 446
446446
447447**Stream idle timeout.** Extra seconds to wait for model output on a streaming response that is sending only keep-alive pings. Gateway provider only. Default 300.
448448
449> **More detail**
449> [accordion] More detail
450450>
451451> With pings arriving (SSE `ping` events or `:` comment lines), sessions accept at least about five minutes of them, then wait this many seconds more. With no pings, a silent response still fails after about 5 minutes whatever this value, so make the gateway send them.
452452>
third-party/claude-desktop/import Changed · +36 / -36 lines
from line 55
5555
5656You can pull your claude.ai history straight into the wizard by signing in, or download it from claude.ai yourself and choose the file.
5757
58**Sign in to claude.ai (recommended)**
58> [tab] Sign in to claude.ai (recommended)
59>
60> Click **Sign in to claude.ai…**. Your browser opens to claude.ai; sign in if prompted, choose your organization if you belong to more than one, and click **Authorize**.
61>
62> 
63>
64> The organization selector, shown if your claude.ai account belongs to more than one workspace.
65>
66> 
67>
68> The authorization prompt. The only permission granted is a one-time export of your own data.
69>
70> Back in Claude Desktop, click **Fetch export**. The wizard requests an export from claude.ai, downloads it, and shows what it found.
71>
72> 
73>
74> The wizard after the export finishes downloading.
5975
60Click **Sign in to claude.ai…**. Your browser opens to claude.ai; sign in if prompted, choose your organization if you belong to more than one, and click **Authorize**.
61
62
63
64The organization selector, shown if your claude.ai account belongs to more than one workspace.
65
66
67
68The authorization prompt. The only permission granted is a one-time export of your own data.
69
70Back in Claude Desktop, click **Fetch export**. The wizard requests an export from claude.ai, downloads it, and shows what it found.
71
72
73
74The wizard after the export finishes downloading.
75
76**Choose a downloaded file**
77
78On claude.ai, go to **Settings → Privacy → Export data** and click **Export**. If you don't see **Export data**, ask a workspace owner to [enable member data export](#enable-member-data-export-admins).
79
80
81
82The Export data page in claude.ai personal settings.
83
84claude.ai emails you a download link when the export is ready. The link expires after 24 hours.
85
86
87
88The export-ready email.
89
90Download the `.zip`, then in the import wizard click **Choose file…** and select it.
91
92
93
94Step 1 with a downloaded export selected.
76> [tab] Choose a downloaded file
77>
78> On claude.ai, go to **Settings → Privacy → Export data** and click **Export**. If you don't see **Export data**, ask a workspace owner to [enable member data export](#enable-member-data-export-admins).
79>
80> 
81>
82> The Export data page in claude.ai personal settings.
83>
84> claude.ai emails you a download link when the export is ready. The link expires after 24 hours.
85>
86> 
87>
88> The export-ready email.
89>
90> Download the `.zip`, then in the import wizard click **Choose file…** and select it.
91>
92> 
93>
94> Step 1 with a downloaded export selected.
9595
9696Click **Continue**, or **Skip this step** if you only want to bring in local sessions.
9797
third-party/claude-desktop/mdm Changed · +24 / -24 lines
from line 99
9999
100100Push the exported configuration through your MDM. The app reads from these locations:
101101
102**macOS**
103
104| Source | Path | Precedence |
105| - | - | - |
106| Managed (per-user) | `/Library/Managed Preferences/<user>/com.anthropic.claudefordesktop.plist` | Highest |
107| Managed (machine) | `/Library/Managed Preferences/com.anthropic.claudefordesktop.plist` | |
108| Local (user) | `~/Library/Application Support/Claude-3p/configLibrary/` | Lowest |
109
110A `.mobileconfig` profile delivered by MDM lands in the Managed Preferences locations automatically. Both managed paths are read; where a key appears in both, the per-user value wins.
111
112**Windows**
113
114| Source | Path | Precedence |
115| - | - | - |
116| Machine policy | `HKLM\SOFTWARE\Policies\Claude` | Highest |
117| User policy | `HKCU\SOFTWARE\Policies\Claude` | |
118| Local (user) | `%LOCALAPPDATA%\Claude-3p\configLibrary\` | Lowest |
119
120A Group Policy Object or Intune configuration profile writes to the registry policy paths. The hives are not merged: when machine policy is present (any `REG_SZ`, `REG_EXPAND_SZ`, or `REG_DWORD` value directly under `HKLM\SOFTWARE\Policies\Claude`, including an empty string, and the key's unnamed default value when set), the app ignores `HKCU\SOFTWARE\Policies\Claude` entirely. Deploy the complete configuration to one hive; machine policy (`HKLM`) is the recommended location.
121
122> [!WARNING]
102> [tab] macOS
123103>
124> Values must sit directly under `HKLM\SOFTWARE\Policies\Claude` or `HKCU\SOFTWARE\Policies\Claude`. The app never reads values nested in a subkey, as some ADMX-based and Policy CSP tooling writes them: they do not apply as configuration and do not count as machine policy being present. Write values as `REG_SZ` (`REG_DWORD` is also accepted for boolean and integer keys and is read as its decimal value). Avoid `REG_EXPAND_SZ`: the app counts it as machine policy being present but cannot read its contents, so a single `REG_EXPAND_SZ` value under `HKLM` disables user policy without supplying any configuration. The app cannot see `REG_QWORD`, `REG_MULTI_SZ`, or `REG_BINARY` values at all.
104> | Source | Path | Precedence |
105> | - | - | - |
106> | Managed (per-user) | `/Library/Managed Preferences/<user>/com.anthropic.claudefordesktop.plist` | Highest |
107> | Managed (machine) | `/Library/Managed Preferences/com.anthropic.claudefordesktop.plist` | |
108> | Local (user) | `~/Library/Application Support/Claude-3p/configLibrary/` | Lowest |
109>
110> A `.mobileconfig` profile delivered by MDM lands in the Managed Preferences locations automatically. Both managed paths are read; where a key appears in both, the per-user value wins.
125111
126> [!NOTE]
112> [tab] Windows
127113>
128> In releases before v1.19367.0, the app read both hives and merged them key by key, with the `HKLM` value winning where a key appeared in both. Fleets that split keys across both hives must consolidate the full configuration into one hive before updating to v1.19367.0 or later.
114> | Source | Path | Precedence |
115> | - | - | - |
116> | Machine policy | `HKLM\SOFTWARE\Policies\Claude` | Highest |
117> | User policy | `HKCU\SOFTWARE\Policies\Claude` | |
118> | Local (user) | `%LOCALAPPDATA%\Claude-3p\configLibrary\` | Lowest |
119>
120> A Group Policy Object or Intune configuration profile writes to the registry policy paths. The hives are not merged: when machine policy is present (any `REG_SZ`, `REG_EXPAND_SZ`, or `REG_DWORD` value directly under `HKLM\SOFTWARE\Policies\Claude`, including an empty string, and the key's unnamed default value when set), the app ignores `HKCU\SOFTWARE\Policies\Claude` entirely. Deploy the complete configuration to one hive; machine policy (`HKLM`) is the recommended location.
121>
122> > [!WARNING]
123> >
124> > Values must sit directly under `HKLM\SOFTWARE\Policies\Claude` or `HKCU\SOFTWARE\Policies\Claude`. The app never reads values nested in a subkey, as some ADMX-based and Policy CSP tooling writes them: they do not apply as configuration and do not count as machine policy being present. Write values as `REG_SZ` (`REG_DWORD` is also accepted for boolean and integer keys and is read as its decimal value). Avoid `REG_EXPAND_SZ`: the app counts it as machine policy being present but cannot read its contents, so a single `REG_EXPAND_SZ` value under `HKLM` disables user policy without supplying any configuration. The app cannot see `REG_QWORD`, `REG_MULTI_SZ`, or `REG_BINARY` values at all.
125>
126> > [!NOTE]
127> >
128> > In releases before v1.19367.0, the app read both hives and merged them key by key, with the `HKLM` value winning where a key appeared in both. Fleets that split keys across both hives must consolidate the full configuration into one hive before updating to v1.19367.0 or later.
129129
130130When a managed source sets any key other than the [app-behavior keys](#update-keys-and-managed-precedence) listed below, the managed configuration takes effect, the in-app configuration window becomes read-only, and locally authored values in `configLibrary/` are ignored.
131131
third-party/claude-desktop/overview Changed · +4 / -4 lines
from line 81
8181
8282## Next steps
8383
84> **[Installation and setup](https://claude.com/docs/third-party/claude-desktop/installation.md)**
84> [card] [Installation and setup](https://claude.com/docs/third-party/claude-desktop/installation.md)
8585>
8686> Roll out Claude Desktop on 3P to your organization, or configure a single machine for evaluation.
8787
88> **[Configuration reference](https://claude.com/docs/third-party/claude-desktop/configuration.md)**
88> [card] [Configuration reference](https://claude.com/docs/third-party/claude-desktop/configuration.md)
8989>
9090> Every managed-configuration key, what it does, and recommended security profiles.
9191
92> **[Extensions](https://claude.com/docs/third-party/claude-desktop/extensions.md)**
92> [card] [Extensions](https://claude.com/docs/third-party/claude-desktop/extensions.md)
9393>
9494> Deploy MCP servers, plugins, skills, and hooks across your fleet.
9595
96> **[Telemetry and egress](https://claude.com/docs/third-party/claude-desktop/telemetry.md)**
96> [card] [Telemetry and egress](https://claude.com/docs/third-party/claude-desktop/telemetry.md)
9797>
9898> What the app sends to Anthropic, how to turn it off, and the firewall allowlist you'll need.
9999
third-party/claude-desktop/status-line Changed · +48 / -48 lines
from line 86
8686
8787Both samples print a budget line, `■■■■■■■■□□ 82% of $500 used this month`. The macOS and Linux sample reads its numbers from a file that your own scheduled job keeps up to date. The Windows sample prints fixed numbers and shows how a PowerShell script prints UTF-8, reads the input, and writes the escape character.
8888
89**macOS and Linux**
89> [tab] macOS and Linux
90>
91> ```sh theme={null}
92> #!/bin/sh
93> # Prints, for example: ■■■■■■■■□□ 82% of $500 used this month
94> # Your own scheduled job keeps this file up to date. It holds dollars used and
95> # the limit as two whole numbers, for example: 410 500
96> BUDGET_FILE=/opt/example/budget.txt
97>
98> # Unless the file holds two whole numbers, print nothing so no line shows.
99> [ -r "$BUDGET_FILE" ] || exit 0
100> read -r used limit < "$BUDGET_FILE"
101> case "$used" in ''|0?*|*[!0-9]*) exit 0 ;; esac
102> case "$limit" in ''|0*|*[!0-9]*) exit 0 ;; esac
103>
104> percent=$((used * 100 / limit))
105> if [ "$percent" -ge 90 ]; then color=31 # red
106> elif [ "$percent" -ge 70 ]; then color=33 # yellow
107> else color=32 # green
108> fi
109>
110> full="" empty=""
111> for step in 10 20 30 40 50 60 70 80 90 100; do
112> if [ "$percent" -ge "$step" ]; then full="${full}■"; else empty="${empty}□"; fi
113> done
114>
115> printf '\033[%sm%s\033[0m%s \033[%sm%s%%\033[0m of $%s used this month\n' \
116> "$color" "$full" "$empty" "$color" "$percent" "$limit"
117> ```
90118
91```sh theme={null}
92#!/bin/sh
93# Prints, for example: ■■■■■■■■□□ 82% of $500 used this month
94# Your own scheduled job keeps this file up to date. It holds dollars used and
95# the limit as two whole numbers, for example: 410 500
96BUDGET_FILE=/opt/example/budget.txt
97
98# Unless the file holds two whole numbers, print nothing so no line shows.
99[ -r "$BUDGET_FILE" ] || exit 0
100read -r used limit < "$BUDGET_FILE"
101case "$used" in ''|0?*|*[!0-9]*) exit 0 ;; esac
102case "$limit" in ''|0*|*[!0-9]*) exit 0 ;; esac
103
104percent=$((used * 100 / limit))
105if [ "$percent" -ge 90 ]; then color=31 # red
106elif [ "$percent" -ge 70 ]; then color=33 # yellow
107else color=32 # green
108fi
109
110full="" empty=""
111for step in 10 20 30 40 50 60 70 80 90 100; do
112 if [ "$percent" -ge "$step" ]; then full="${full}■"; else empty="${empty}□"; fi
113done
114
115printf '\033[%sm%s\033[0m%s \033[%sm%s%%\033[0m of $%s used this month\n' \
116 "$color" "$full" "$empty" "$color" "$percent" "$limit"
117```
118
119**Windows**
120
121```powershell theme={null}
122# Print UTF-8, so that characters outside ASCII show correctly.
123[Console]::OutputEncoding = New-Object Text.UTF8Encoding $false
124
125# Read the session data, one line of JSON. Use fields such as $session.model.display_name.
126$line = [Console]::In.ReadLine()
127$session = $line | ConvertFrom-Json
128
129# Fixed numbers keep the sample short. Replace them with your own budget data.
130$esc = [char]27
131$yellow = $esc + '[33m'
132$reset = $esc + '[0m'
133$full = ([string][char]0x25A0) * 8
134$empty = ([string][char]0x25A1) * 2
135$bar = $yellow + $full + $reset + $empty
136Write-Output ($bar + ' ' + $yellow + '82%' + $reset + ' of $500 used this month')
137```
119> [tab] Windows
120>
121> ```powershell theme={null}
122> # Print UTF-8, so that characters outside ASCII show correctly.
123> [Console]::OutputEncoding = New-Object Text.UTF8Encoding $false
124>
125> # Read the session data, one line of JSON. Use fields such as $session.model.display_name.
126> $line = [Console]::In.ReadLine()
127> $session = $line | ConvertFrom-Json
128>
129> # Fixed numbers keep the sample short. Replace them with your own budget data.
130> $esc = [char]27
131> $yellow = $esc + '[33m'
132> $reset = $esc + '[0m'
133> $full = ([string][char]0x25A0) * 8
134> $empty = ([string][char]0x25A1) * 2
135> $bar = $yellow + $full + $reset + $empty
136> Write-Output ($bar + ' ' + $yellow + '82%' + $reset + ' of $500 used this month')
137> ```
138138
139139## When the status line updates
140140
third-party/claude-desktop/telemetry Changed · +48 / -48 lines
from line 175
175175
176176The host(s) for your configured provider. Conversation content goes to the host whose purpose is model inference.
177177
178**Google Cloud's Agent Platform**
178> [tab] Google Cloud's Agent Platform
179>
180> | Host | Purpose |
181> | - | - |
182> | `<region>-aiplatform.googleapis.com` | Model inference for single regions. The `global` region uses `aiplatform.googleapis.com`, and the `eu` / `us` multi-regions use `aiplatform.eu.rep.googleapis.com` / `aiplatform.us.rep.googleapis.com`. Replaced by the host of `inferenceVertexBaseUrl` if set. |
183> | `oauth2.googleapis.com` | Google auth token exchange |
184> | `sts.googleapis.com` | Google auth token exchange |
185> | `accounts.google.com` | Google auth token exchange |
186> | `iamcredentials.googleapis.com` | Google auth token exchange |
179187
180| Host | Purpose |
181| - | - |
182| `<region>-aiplatform.googleapis.com` | Model inference for single regions. The `global` region uses `aiplatform.googleapis.com`, and the `eu` / `us` multi-regions use `aiplatform.eu.rep.googleapis.com` / `aiplatform.us.rep.googleapis.com`. Replaced by the host of `inferenceVertexBaseUrl` if set. |
183| `oauth2.googleapis.com` | Google auth token exchange |
184| `sts.googleapis.com` | Google auth token exchange |
185| `accounts.google.com` | Google auth token exchange |
186| `iamcredentials.googleapis.com` | Google auth token exchange |
188> [tab] Amazon Bedrock
189>
190> | Host | Purpose |
191> | - | - |
192> | `bedrock-runtime.<region>.amazonaws.com` | Model inference. Replaced by the host of `inferenceBedrockBaseUrl` if set. |
193> | `bedrock.<region>.amazonaws.com` | Control plane (model discovery) |
194> | `sts.amazonaws.com`, `sts.<region>.amazonaws.com` | STS token exchange (profile auth only) |
195> | `portal.sso.<sso-region>.amazonaws.com`, `oidc.<sso-region>.amazonaws.com` | IAM Identity Center sign-in and token refresh, for [in-app AWS sign-in](https://claude.com/docs/third-party/claude-desktop/bedrock.md#in-app-aws-sign-in) and for named profiles that use IAM Identity Center. `<sso-region>` is `inferenceBedrockSsoRegion` (or the profile's `sso_region`) and can differ from the inference region. |
196>
197> With `inferenceBedrockBearerToken` set, the runtime and control-plane hosts are required.
198>
199> For AWS GovCloud regions (`us-gov-*`), the app automatically uses the FIPS endpoints instead: `bedrock-runtime-fips.<region>.amazonaws.com` and `bedrock-fips.<region>.amazonaws.com`.
187200
188**Amazon Bedrock**
201> [tab] Amazon Bedrock Mantle
202>
203> | Host | Purpose |
204> | - | - |
205> | `bedrock-mantle.<region>.api.aws` | Model inference. Replaced by the host of `inferenceBedrockBaseUrl` if set. |
189206
190| Host | Purpose |
191| - | - |
192| `bedrock-runtime.<region>.amazonaws.com` | Model inference. Replaced by the host of `inferenceBedrockBaseUrl` if set. |
193| `bedrock.<region>.amazonaws.com` | Control plane (model discovery) |
194| `sts.amazonaws.com`, `sts.<region>.amazonaws.com` | STS token exchange (profile auth only) |
195| `portal.sso.<sso-region>.amazonaws.com`, `oidc.<sso-region>.amazonaws.com` | IAM Identity Center sign-in and token refresh, for [in-app AWS sign-in](https://claude.com/docs/third-party/claude-desktop/bedrock.md#in-app-aws-sign-in) and for named profiles that use IAM Identity Center. `<sso-region>` is `inferenceBedrockSsoRegion` (or the profile's `sso_region`) and can differ from the inference region. |
207> [tab] Microsoft Foundry
208>
209> | Host | Purpose |
210> | - | - |
211> | `<resource>.services.ai.azure.com` | Model inference. Replaced by the host of `inferenceFoundryBaseUrl` if set. |
212> | `login.microsoftonline.com` | Entra ID auth (interactive sign-in only) |
196213
197With `inferenceBedrockBearerToken` set, the runtime and control-plane hosts are required.
214> [tab] Gateway
215>
216> | Host | Purpose |
217> | - | - |
218> | Host of `inferenceGatewayBaseUrl` | Model inference |
198219
199For AWS GovCloud regions (`us-gov-*`), the app automatically uses the FIPS endpoints instead: `bedrock-runtime-fips.<region>.amazonaws.com` and `bedrock-fips.<region>.amazonaws.com`.
200
201**Amazon Bedrock Mantle**
202
203| Host | Purpose |
204| - | - |
205| `bedrock-mantle.<region>.api.aws` | Model inference. Replaced by the host of `inferenceBedrockBaseUrl` if set. |
206
207**Microsoft Foundry**
208
209| Host | Purpose |
210| - | - |
211| `<resource>.services.ai.azure.com` | Model inference. Replaced by the host of `inferenceFoundryBaseUrl` if set. |
212| `login.microsoftonline.com` | Entra ID auth (interactive sign-in only) |
213
214**Gateway**
215
216| Host | Purpose |
217| - | - |
218| Host of `inferenceGatewayBaseUrl` | Model inference |
219
220**Claude API**
221
222| Host | Purpose |
223| - | - |
224| `api.anthropic.com` | Model inference; token exchange, renewal, and revocation for browser sign-in |
225| `platform.claude.com` | Browser sign-in page. Dialed only when no static key or credential helper is configured. Browser sign-in also needs the hosts that serve the browser check on the sign-in and approval pages, listed under [Optional features](#optional-features). |
220> [tab] Claude API
221>
222> | Host | Purpose |
223> | - | - |
224> | `api.anthropic.com` | Model inference; token exchange, renewal, and revocation for browser sign-in |
225> | `platform.claude.com` | Browser sign-in page. Dialed only when no static key or credential helper is configured. Browser sign-in also needs the hosts that serve the browser check on the sign-in and approval pages, listed under [Optional features](#optional-features). |
226226
227227### Auto-updates (`disableAutoUpdates: false`)
228228
third-party/claude-desktop/vertex Changed · +3 / -3 lines
from line 357
357357
358358One of: `browser`, `broker`
359359
360> **More detail**
360> [accordion] More detail
361361>
362362> * **`browser`:** register the redirect URI `http://127.0.0.1:<port>/callback` with your identity provider (for Entra, `http://127.0.0.1/callback`).
363363> * **`broker`:** uses Web Account Manager on Windows or Company Portal on macOS, and does not work on Linux. It can satisfy Conditional Access policies that require a compliant or managed device, or token protection.
from line 376
376376
377377**Workforce Identity IdP (OIDC).** Your organization’s OpenID Connect identity provider. Users sign in there, and the app exchanges their ID token at GCP STS.
378378
379> **Child attributes (9)**
379> [accordion] Child attributes (9)
380380>
381381> **clientId** `string` *required*
382382>
from line 416
416416>
417417> Space-separated hostnames also accepted as the referrer of the sign-in callback, besides the authorization URL’s host.
418418>
419> > **More detail**
419> > [accordion] More detail
420420> >
421421> > If a callback is rejected for a referrer mismatch, the app log names the rejected host. Add that hostname here.
422422
claude-science/auto-mode Changed · +1 / -1 lines
from line 10
1010
1111## Turn auto mode on or off
1212
13Where available, auto mode is enabled by default for Pro, Max, and Team plans and off by default for Enterprise plans. Once an Enterprise admin enables auto mode, it will automatically become the default for all employees in the org.
13Where available, auto mode is enabled by default for Pro, Max, Ultra, and Team plans and off by default for Enterprise plans. Once an Enterprise admin enables auto mode, it will automatically become the default for all employees in the org.
1414
1515* **You can adjust the default for new sessions** by going to **Settings > Permissions** and toggling **Auto mode on for new sessions** to your preferred setting.
1616* **You can adjust the default for the current session**, by opening the session settings menu in the message box and toggling **Auto mode** to your preferred setting.
claude-science/connectors-and-skills Changed · +1 / -1 lines
from line 46
4646If what you need still isn't there, try these:
4747
4848* **Ask Claude first.** Many public databases and tools work without a connector, because the code Claude runs can reach websites directly. The first time Claude needs a new site, a permission card asks you to allow it. If your organization manages the list of allowed sites, ask an admin to add it. See [Sandbox](https://claude.com/docs/claude-science/core-concepts.md#sandbox).
49* **Add one from the Connectors Directory.** Go to **Settings > Connectors > Add connector > Browse Connectors Directory**, which opens the directory in claude.ai. On Pro and Max plans, add the connector there and it appears in Claude Science. On Team and Enterprise plans, you may be able to add it yourself; if not, an admin can add it for your organization. On a Team plan, select **Request** on the connector's listing to ask your admins.
49* **Add one from the Connectors Directory.** Go to **Settings > Connectors > Add connector > Browse Connectors Directory**, which opens the directory in claude.ai. On Pro, Max, and Ultra plans, add the connector there and it appears in Claude Science. On Team and Enterprise plans, you may be able to add it yourself; if not, an admin can add it for your organization. On a Team plan, select **Request** on the connector's listing to ask your admins.
5050* **Add one yourself.** If the tool's maker gives you a web address for its connector (sometimes called an MCP server URL), go to **Settings > Connectors > Add connector > Remote URL** and paste it in. If the maker gives you a command to run instead, choose **Local command** and enter it there. On Team and Enterprise plans, this works only if your organization allows custom connectors. See [Custom connectors](https://claude.com/docs/claude-science/custom-connectors.md).
5151* **Ask the tool's maker.** If no connector exists yet, ask them to build one and [submit it to the Connectors Directory](https://claude.com/docs/connectors/building/submission.md).
5252
claude-science/enable-claude-science Changed · +2 / -2 lines
from line 13
1313| Team | Off; turn on in **Organization settings** |
1414| Claude Team plan for scientists | On; turn off in **Organization settings** |
1515| Enterprise | Off; turn on in **Organization settings** |
16| Pro and Max | On; no admin action needed |
16| Pro, Max, and Ultra | On; no admin action needed |
1717| Free | Not available |
1818
1919On the Claude Team plan for scientists, members can [download Claude Science](https://claude.com/product/claude-science) and sign in with their claude.ai account without any admin action. An Owner or Primary Owner can [turn Claude Science off](#turn-off-claude-science) or change the other [organization settings](https://claude.com/docs/claude-science/admin-controls.md#organization-settings) at any time in [**Organization settings > Claude Science**](https://claude.ai/admin-settings/claude-science). The **PubMed**, **Clinical Trials**, **ChEMBL**, and **bioRxiv** connectors aren't added to your organization automatically (see [Set up connectors](#set-up-connectors)).
from line 66
6666
6767If the **Enable for your organization** toggle is off, members are stopped at sign-in with a message such as "Your organization hasn't turned on Claude Science yet. Ask your admins for access." They can select **Request access** to send that request to the organization's admins, then sign in again once Claude Science is on. On Enterprise plans, members whose custom role doesn't include the capability are stopped the same way, with a message that Claude Science isn't available for their account yet, and can also request access. These requests appear under **Requests** in **Organization settings** > **Notifications**. Turning Claude Science on resolves them, and for a member whose custom role lacks the capability, you give the role access on the **Roles** page.
6868
69Members who belong to more than one organization on claude.ai, such as a personal account alongside yours, need to choose your organization when claude.ai asks which one to connect. Before they select **Authorize**, they can also select **Switch organization** on the authorization screen to change that choice. A member who connects a Free personal account instead sees "Claude Science requires a Pro or Max subscription." and can select **Switch account** to sign in again and choose your organization.
69Members who belong to more than one organization on claude.ai, such as a personal account alongside yours, need to choose your organization when claude.ai asks which one to connect. Before they select **Authorize**, they can also select **Switch organization** on the authorization screen to change that choice. A member who connects a Free personal account instead sees "Claude Science requires a Pro, Max, or Ultra subscription." and can select **Switch account** to sign in again and choose your organization.
7070
7171## HIPAA organizations
7272
claude-science/run-on-remote-linux-server Changed · +1 / -1 lines
from line 8
88>
99> This page covers running all of Claude Science on a remote machine. To keep Claude Science on your own computer and have it run jobs on a machine you reach over SSH, see [Remote compute clusters](https://claude.com/docs/claude-science/remote-compute-clusters.md).
1010
11The server needs x64 Linux on a glibc-based distribution (arm64 and musl-based distributions such as Alpine aren't supported), about 10 GB of free disk space, and the system packages below. Your Claude account needs a Pro, Max, Team, or Enterprise plan; see [Requirements](https://claude.com/docs/claude-science/overview.md#requirements).
11The server needs x64 Linux on a glibc-based distribution (arm64 and musl-based distributions such as Alpine aren't supported), about 10 GB of free disk space, and the system packages below. Your Claude account needs a Pro, Max, Ultra, Team, or Enterprise plan; see [Requirements](https://claude.com/docs/claude-science/overview.md#requirements).
1212
1313## Install dependencies
1414
claude-science/the-reviewer Changed · +2 / -2 lines
from line 2
22
33> A built-in verification step that independently re-reads Claude's recent responses, the approved plan, saved artifacts, and the execution record, then checks whether its claims match what ran.
44
5The reviewer is a built-in verification step that independently re-reads Claude's recent responses, the approved plan, saved artifacts, and the execution record, then checks whether Claude's claims match what actually ran. It runs automatically after responses and periodically during long work, and you can trigger it any time with **Request review**. Automatic review is on by default on Max, Team, and Enterprise plans; on the Pro plan it starts off, and you can turn it on per session.
5The reviewer is a built-in verification step that independently re-reads Claude's recent responses, the approved plan, saved artifacts, and the execution record, then checks whether Claude's claims match what actually ran. It runs automatically after responses and periodically during long work, and you can trigger it any time with **Request review**. Automatic review is on by default on Max, Ultra, Team, and Enterprise plans; on the Pro plan it starts off, and you can turn it on per session.
66
77## Examples of what the reviewer checks
88
from line 25
2525
2626## Controls
2727
28Auto-review is a per-session toggle in the session settings menu. It starts on for Max, Team, and Enterprise plans and off for the Pro plan. If you turn Auto-review off while Claude is working, no new automatic reviews start, including for delegated work that is already running. Reviews that have already started or are waiting to start still finish. Turning Auto-review back on resumes automatic reviews, starting with the work done while it was off. Reviews run against your plan's usage.
28Auto-review is a per-session toggle in the session settings menu. It starts on for Max, Ultra, Team, and Enterprise plans and off for the Pro plan. If you turn Auto-review off while Claude is working, no new automatic reviews start, including for delegated work that is already running. Reviews that have already started or are waiting to start still finish. Turning Auto-review back on resumes automatic reviews, starting with the work done while it was off. Reviews run against your plan's usage.
2929
claude-tag/admins/migrate-from-earlier Changed · +1 / -1 lines
from line 44
4444
4545> [!WARNING]
4646>
47> Since October 5, 2026, the earlier Claude in Slack app, shown as **Legacy** in admin settings, no longer answers in channels of a workspace paired with your Claude organization. A channel there that's still set to Legacy gets a notice that the legacy bot is retired, until you set **Claude Tag version** to **New** on the channel, or on its workspace if the channel inherits the setting. You also can't switch a workspace or channel to Legacy anymore. Direct messages aren't affected. In a workspace that isn't paired, Pro and Max users still get answers from the earlier app in channels, and anyone else with a connected Claude account gets the [workspace setup notice](https://claude.com/docs/claude-tag/admins/troubleshooting.md#this-workspace-isn%E2%80%99t-set-up-for-claude-tag-yet) instead.
47> Since October 5, 2026, the earlier Claude in Slack app, shown as **Legacy** in admin settings, no longer answers in channels of a workspace paired with your Claude organization. A channel there that's still set to Legacy gets a notice that the legacy bot is retired, until you set **Claude Tag version** to **New** on the channel, or on its workspace if the channel inherits the setting. You also can't switch a workspace or channel to Legacy anymore. Direct messages aren't affected. In a workspace that isn't paired, Pro, Max, and Ultra users still get answers from the earlier app in channels, and anyone else with a connected Claude account gets the [workspace setup notice](https://claude.com/docs/claude-tag/admins/troubleshooting.md#this-workspace-isn%E2%80%99t-set-up-for-claude-tag-yet) instead.
4848
4949## What stays the same
5050
claude-tag/admins/troubleshooting Changed · +1 / -1 lines
from line 23
2323
2424| You expected | But got | Do this |
2525| :- | :- | :- |
26| The setup page at [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag) | A page titled **Set up Claude Tag** with **View setup guide** and **Go to chat** buttons | Your signed-in account can't run setup, and **View setup guide** leads back to this guide. On a personal account (Free, Pro, or Max), [start a Team or Enterprise plan](https://claude.com/pricing) first. In a Team or Enterprise organization, ask an Owner to run setup. When the page shows a workspace switcher, your account also belongs to another Team or Enterprise organization; switch to it and retry. |
26| The setup page at [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag) | A page titled **Set up Claude Tag** with **View setup guide** and **Go to chat** buttons | Your signed-in account can't run setup, and **View setup guide** leads back to this guide. On a personal account (Free, Pro, Max, or Ultra), [start a Team or Enterprise plan](https://claude.com/pricing) first. In a Team or Enterprise organization, ask an Owner to run setup. When the page shows a workspace switcher, your account also belongs to another Team or Enterprise organization; switch to it and retry. |
2727| A pairing code from `@Claude connect` | “Only Slack workspace admins (or Enterprise Grid org admins) can link this workspace to a Claude organization…” | The person who sent `@Claude connect` isn't a Slack workspace admin or Grid org admin. See [Only Slack workspace admins or Grid org admins can link this workspace](#only-slack-workspace-admins-or-grid-org-admins-can-link-this-workspace). |
2828| A pairing code | “…installation is out of date” | A Slack admin approves the update or reinstalls the app, then sends `@Claude connect` again. See [This workspace's Claude app installation is out of date](#this-workspace%E2%80%99s-claude-app-installation-is-out-of-date). |
2929| A pairing code | A message about guests, or about the channel being shared across workspaces | Send `@Claude connect` again in a channel with no guests that belongs to a single workspace. Match the exact message in [Guest and shared channels](#guest-and-shared-channels) for the fix that fits it. |
claude-tag/users/models Changed · +1 / -1 lines
from line 8
88
99Every Claude Tag reply in Slack comes from one Claude model, and you choose which one by asking Claude for it in plain language, the same way you hand it any other task. The footer of each reply names the model that handled it, so you can confirm a switch took effect.
1010
11Model choice is part of Claude Tag, which is available on Team and Enterprise plans. It isn't available on individual plans (Free, Pro, or Max) or for third-party deployments.
11Model choice is part of Claude Tag, which is available on Team and Enterprise plans. It isn't available on individual plans (Free, Pro, Max, or Ultra) or for third-party deployments.
1212
1313Which models you can ask for depends on your organization; see [which models you can use](#which-models-you-can-use).
1414
claude-tag/users/use-cases/catch-up Changed · +2 / -2 lines
from line 46
4646
4747## Related resources
4848
49> **[Turn threads into docs and tickets](https://claude.com/docs/claude-tag/users/use-cases/create-artifacts.md)**
49> [card] [Turn threads into docs and tickets](https://claude.com/docs/claude-tag/users/use-cases/create-artifacts.md)
5050>
5151> When the catch-up should become an artifact
5252
53> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
53> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
5454>
5555> Scheduling and triggers
5656
claude-tag/users/use-cases/create-artifacts Changed · +2 / -2 lines
from line 73
7373
7474## Related resources
7575
76> **[Catch up](https://claude.com/docs/claude-tag/users/use-cases/catch-up.md)**
76> [card] [Catch up](https://claude.com/docs/claude-tag/users/use-cases/catch-up.md)
7777>
7878> When you need the summary, not the artifact
7979
80> **[Good habits](https://claude.com/docs/claude-tag/users/good-habits.md)**
80> [card] [Good habits](https://claude.com/docs/claude-tag/users/good-habits.md)
8181>
8282> How to specify outputs that come back right
8383
claude-tag/users/use-cases/find-answers Changed · +2 / -2 lines
from line 60
6060
6161## Related resources
6262
63> **[Catch up](https://claude.com/docs/claude-tag/users/use-cases/catch-up.md)**
63> [card] [Catch up](https://claude.com/docs/claude-tag/users/use-cases/catch-up.md)
6464>
6565> The same mechanism pointed at "what did I miss"
6666
67> **[What Claude Tag remembers](https://claude.com/docs/claude-tag/users/memory.md)**
67> [card] [What Claude Tag remembers](https://claude.com/docs/claude-tag/users/memory.md)
6868>
6969> How channel knowledge accumulates
7070
claude-tag/users/use-cases/fix-bugs Changed · +2 / -2 lines
from line 78
7878
7979## Related resources
8080
81> **[Watch monitors and alerts](https://claude.com/docs/claude-tag/users/use-cases/watch-monitors.md)**
81> [card] [Watch monitors and alerts](https://claude.com/docs/claude-tag/users/use-cases/watch-monitors.md)
8282>
8383> Catching the problem before the bug report
8484
85> **[Good habits](https://claude.com/docs/claude-tag/users/good-habits.md)**
85> [card] [Good habits](https://claude.com/docs/claude-tag/users/good-habits.md)
8686>
8787> Definitions of done for code tasks
8888
claude-tag/users/use-cases/marketing-team Changed · +2 / -2 lines
from line 105
105105
106106## Related resources
107107
108> **[Pull deal and account state](https://claude.com/docs/claude-tag/users/use-cases/pull-deal-state.md)**
108> [card] [Pull deal and account state](https://claude.com/docs/claude-tag/users/use-cases/pull-deal-state.md)
109109>
110110> The full set of go-to-market prompts
111111
112> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
112> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
113113>
114114> How the scheduled digest runs, and more recipes
115115
claude-tag/users/use-cases/pull-deal-state Changed · +2 / -2 lines
from line 60
6060
6161## Related resources
6262
63> **[Answer data questions](https://claude.com/docs/claude-tag/users/use-cases/answer-data-questions.md)**
63> [card] [Answer data questions](https://claude.com/docs/claude-tag/users/use-cases/answer-data-questions.md)
6464>
6565> When the question is metrics, not accounts
6666
67> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
67> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
6868>
6969> Scheduled digests
7070
claude-tag/users/use-cases/review-documents Changed · +2 / -2 lines
from line 78
7878
7979## Related resources
8080
81> **[Find answers in your docs](https://claude.com/docs/claude-tag/users/use-cases/find-answers.md)**
81> [card] [Find answers in your docs](https://claude.com/docs/claude-tag/users/use-cases/find-answers.md)
8282>
8383> The same connections pointed at a single question
8484
85> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
85> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
8686>
8787> How the recurring review runs on a schedule
8888
claude-tag/users/use-cases/track-projects Changed · +2 / -2 lines
from line 57
5757
5858## Related resources
5959
60> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
60> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
6161>
6262> Schedules and event triggers
6363
64> **[Good habits](https://claude.com/docs/claude-tag/users/good-habits.md)**
64> [card] [Good habits](https://claude.com/docs/claude-tag/users/good-habits.md)
6565>
6666> Definitions of done that close threads
6767
claude-tag/users/use-cases/triage-requests Changed · +2 / -2 lines
from line 74
7474
7575## Related resources
7676
77> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
77> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
7878>
7979> How the weekly rollup runs on a schedule
8080
81> **[What Claude Tag remembers](https://claude.com/docs/claude-tag/users/memory.md)**
81> [card] [What Claude Tag remembers](https://claude.com/docs/claude-tag/users/memory.md)
8282>
8383> How the standing role persists and improves
8484
claude-tag/users/use-cases/work-with-github Changed · +2 / -2 lines
from line 116
116116
117117## Related resources
118118
119> **[Fix bugs](https://claude.com/docs/claude-tag/users/use-cases/fix-bugs.md)**
119> [card] [Fix bugs](https://claude.com/docs/claude-tag/users/use-cases/fix-bugs.md)
120120>
121121> The full arc from a bug report to a draft pull request and green CI
122122
123> **[Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)**
123> [card] [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md)
124124>
125125> Pull request subscriptions and other standing work
126126