The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added sinceA small documentation edit on Control MCP server access for your organization touched a line naming allowedMcpServers after this was published.* [Server-managed settings](/docs/en/server-managed-settings): deliver `allowedMcpServers` and `deniedMcpServers` from the claude.ai admin consolemanaged-mcpsee the edit
Confirmed sinceAnthropic's documentation has since written up fallbackModel, on All settings.| Restriction allowlists | Takes the list whole from the highest source that sets it, without adding entries from lower sources. When the highest source doesn't set one, takes it whole from the next source down | [`availableModels`](#avail…settings-referencesee the edit
Confirmed sinceAnthropic's documentation has since written up allowedMcpServers, on All settings.| Restriction allowlists | Takes the list whole from the highest source that sets it, without adding entries from lower sources. When the highest source doesn't set one, takes it whole from the next source down | [`availableModels`](#avail…settings-referencesee the edit
Confirmed sinceAnthropic's documentation has since written up allowedHttpHookUrls, on Deploy managed settings.| `allowedHttpHookUrls` | Claude Code enforces an empty managed [allowlist](/docs/en/settings-reference#allowedhttphookurls) until you fix the value, so an HTTP hook runs only if another settings file lists its URL. If only an individual e…managed-settingssee the edit
How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up allowedHttpHookUrls, on Deploy managed settings.
Anthropic's release notes agreeChanged managedSourcesBehavior: "merge" to take sandbox.credentials.awsPairs and sandbox.ripgrep whole from the highest managed source that…