ToolingPublished All news from that day
Anthropic added a security center in beta and made inference hooks generally available for Claude Enterprise.
A new admin console at admin.claude.com manages single sign-on and Compliance API keys across a parent organization's Claude organizations.
Check our sources · 7 facts from 2 sourcesClaude Enterprise admins can now check Claude's security settings against Anthropic's recommended configuration on one page, and send prompts and tool calls to their own data security tools. Anthropic published the update on 5 November 2026 in a blog post and in its release notes.
The security center is in beta. Inference hooks, which come as prompt hooks and pre-tool-call hooks, are generally available.
A new admin console at admin.claude.com lets a parent organization manage single sign-on, directory sync, domain verification, groups and Compliance API keys once for all its Claude Enterprise and Claude Platform organizations.
Admins can also sign a member out through the Admin API, manage their IP allowlist themselves, and block personal Claude accounts in Claude Desktop on managed computers. Anthropic says the security center is guidance, not a certification of compliance.
Underlined sentences link to the facts we checked. Dotted words open a short explainer.
Fact 3 of 7 · from Anthropic, 5 Nov 2026
both now generally available
Fact 6 of 7 · from Anthropic, 5 Nov 2026
sign a member out of Claude with a single Admin API call; Enterprise admins can now set up and manage their IP allowlist themselves; block personal and other outside Claude accounts in Claude Desktop on managed computers
Fact 7 of 7 · from Anthropic, 5 Nov 2026
The security center is guidance based on Anthropic's recommendations, not a certification or a guarantee of compliance with any law or standard.
Your reaction
We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.
We count reactions per story and day, never who reacted. They help choose what goes in the monthly issue.
Check our sources
Every sentence above is checked against these 2 sources.
1 Claude release notes
Open the source archived copy-
Anthropic's release notes dated 5 November 2026 list new security and admin features for Claude Enterprise: a security center, inference hooks, centralized management and additional access controls, several in beta.
cite
2 More visibility and control over Claude Enterprise for security teams
Open the source archived copy-
The security center compares an organization's Claude settings with Anthropic's recommended configuration, and the security center is in beta.
citecompares settings with Anthropic's recommended configuration ... The security center is in beta.
-
Inference hooks, both prompt hooks and pre-tool-call hooks, are generally available.
citeboth now generally available
-
Prompt hooks send prompts from supported Claude products to the customer's security tool for a check, and pre-tool-call hooks check tool calls before they run.
citePrompt hooks send prompts from supported Claude products to your security tool for a check. Pre-tool-call hooks check tool calls in supported Claude products before they run.
-
Centralized management gives a parent organization an admin console at admin.claude.com for single sign-on, directory sync (SCIM), domain verification, groups and Compliance API keys across its Claude Enterprise and Claude Platform organizations.
citeits own admin console at admin.claude.com ... These settings include single sign-on, directory sync (SCIM), domain verification, groups, and Compliance API keys ... across its Claude Enterprise and Claude Platform organizations
-
Admins can sign a member out of Claude with a single Admin API call, manage their IP allowlist themselves, and block personal and other outside Claude accounts in Claude Desktop on managed computers.
citesign a member out of Claude with a single Admin API call; Enterprise admins can now set up and manage their IP allowlist themselves; block personal and other outside Claude accounts in Claude Desktop on managed computers
-
Anthropic says the security center is guidance based on its recommendations, not a certification or a guarantee of compliance with any law or standard.
citeThe security center is guidance based on Anthropic's recommendations, not a certification or a guarantee of compliance with any law or standard.
Every sentence above is checked against these 2 sources. Each fact has its own address you can cite.
Source 1 · Anthropic · 5 Nov 2026
Claude release notes
Anthropic's release notes dated 5 November 2026 list new security and admin features for Claude Enterprise: a security center, inference hooks, centralized management and additional access controls, several in beta.
Source 2 · Anthropic · 5 Nov 2026
More visibility and control over Claude Enterprise for security teams
The security center compares an organization's Claude settings with Anthropic's recommended configuration, and the security center is in beta.
compares settings with Anthropic's recommended configuration ... The security center is in beta.
Inference hooks, both prompt hooks and pre-tool-call hooks, are generally available.
both now generally available
Prompt hooks send prompts from supported Claude products to the customer's security tool for a check, and pre-tool-call hooks check tool calls before they run.
Prompt hooks send prompts from supported Claude products to your security tool for a check. Pre-tool-call hooks check tool calls in supported Claude products before they run.
Show all 6 factsShow fewer facts
Centralized management gives a parent organization an admin console at admin.claude.com for single sign-on, directory sync (SCIM), domain verification, groups and Compliance API keys across its Claude Enterprise and Claude Platform organizations.
its own admin console at admin.claude.com ... These settings include single sign-on, directory sync (SCIM), domain verification, groups, and Compliance API keys ... across its Claude Enterprise and Claude Platform organizations
Admins can sign a member out of Claude with a single Admin API call, manage their IP allowlist themselves, and block personal and other outside Claude accounts in Claude Desktop on managed computers.
sign a member out of Claude with a single Admin API call; Enterprise admins can now set up and manage their IP allowlist themselves; block personal and other outside Claude accounts in Claude Desktop on managed computers
Anthropic says the security center is guidance based on its recommendations, not a certification or a guarantee of compliance with any law or standard.
The security center is guidance based on Anthropic's recommendations, not a certification or a guarantee of compliance with any law or standard.
Topics
The morning email
On the mornings we publish: the three top stories and up to four short ones. Free.
We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep