Fetching from the wire…
Public story · 2026-07-20 · high
The beta adds role, invite, and group management, but plain member removal is the piece that actually matters.
Why now: The beta appears in the July 20 briefing of Anthropic's release notes, which don't say when the beta tag comes off the group and role endpoints.
Anthropic released an Admin API beta for Claude Enterprise, adding endpoints to list members, change roles, and remove members, per release notes on releasebot.io.
Manual seat removal has been the default, and it's the reason former employees keep active Claude access after they leave. Wiring member removal into an identity provider's offboarding flow closes that gap without someone remembering to do it by hand.
The beta header, anthropic-beta: ce-user-management-2026-07-13, applies to group and custom-role endpoints only, per the release notes. Member listing, lookup, removal, and invites aren't behind that flag, which makes them the safer place to start building.
This is aimed at teams that have been adding and removing Claude seats manually. The Admin API gives those actions an endpoint instead of a UI click. That endpoint can be called from whatever already runs onboarding and offboarding, an identity provider, an HR tool, a termination script.
That gap is worth watching. If Anthropic leaves member removal outside the beta gate while group and role management stay behind it, that's a signal. Removal is meant to be depended on, not merely tested.
Each link below shares sources, entities, or timing with this story.
Anthropic introduced enterprise-managed MCP connector access starting with Okta, letting admins provision a connector once so users get zero-touch access on first login, with centralized authorization across Claude chat, Claude Code, and Cowork on Team and Enterprise plans. Th...
Files API gets expiration, pagination and 1 TB storage per organization; Agent Skills gets the /v1/skills endpoint; Admin API gets user-management endpoints for Enterprise orgs. Managed Agents gained allowed_domains and blocked_domains over web access, self-hosted sandbox supp...
Anthropic launched a public beta of Claude Code and Cowork inside Claude for Government Desktop, with tamper-evident audit logs and spend governance for agencies. The tamper-evident logging is the notable differentiator, an agent-oversight feature aimed squarely at regulated d...
Beta for Claude Enterprise as of August 11: server-hosted transcripts covering prompts and responses, web and MCP tool-call content, skills and artifacts content captured as transcript text, plus verified user ID and email, org ID, session and per-message IDs, timestamps (Anth...
43.3% on Frontier-Bench v0.1. Opus 4.8 scored 18.7%. That's not an incremental bump, that's the same benchmark with a different shape of answer. Anthropic released Claude Opus 5 on July 24 at $5/$25 per million input/output tokens, exactly half of Fable 5's $10/$50, while matc...
You can import design systems from a GitHub repo, design files, or uploads, and Claude builds against those components, checks its output, and auto-corrects before showing results, with an admin role to lock one approved system org-wide. It also fixes the token-burn problem, o...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.