Urgent.News

What's breaking now, across thousands of outlets.

AI

“Signing in to your company’s plugins one by one is annoying”: Anthropic’s fix puts Claude in the identity business

Anthropic is now letting businesses automatically connect employees to approved Claude plugins, saving staff from having to sign in to The post “Signing in to your company’s plugins one by one is annoying”: Anthropic’s fix puts Claude in the identity business appeared first on The New Stack .

“Signing in to your company’s plugins one by one is annoying”: Anthropic’s fix puts Claude in the identity business

Anthropic is streamlining access to company-approved Claude plugins for employees, eliminating the need for individual sign-ins and authorizations. This new feature enhances user experience and simplifies access management. Anthropic's Enterprise-Managed Authorization (EMA) extension, launched in June, enables central management of MCP connections through existing identity providers.

Okta was the first to adopt this extension, but limited support from other providers has left many organizations still requiring manual authorizations. Now, Claude itself can issue signed identity assertions for participating MCP services, allowing businesses to enable automatic connections without relying on their identity provider's EMA support.

Implementing this feature is straightforward for Team and Enterprise customers, with Anthropic providing guidance for developers creating compatible MCP servers. The beta version of this feature is now available to businesses, with Claude taking on the role of identity verification when employees access third-party services through the plugins.

Anthropic encourages other companies to adopt the feature, noting that it can enhance user experience and simplify access management.

Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at thenewstack.io →

More in AI

Google Changes AI Access Rules for Schools Ahead of 2027

Google's new school AI controls could affect student Search access. Here's what administrators need to know about Gemini, Guided Learning, and the 2027 rollout.

  • Google to implement stricter AI access controls for K-12 students in 2027.
  • Schools can opt out of Google's AI tools, including Gemini and NotebookLM.
  • Disabling AI services will revoke access to Google Search for student accounts.

Pangram releases Pangram Image 1.0, which it says is state-of-the-art in AI image detection, and Image Flash 1.0, which powers its AI video detection (Isaac Kasahara/Pangram)

State-of-the-art AI image and video detection with our latest Pangram Image models. … A few months ago, we released Pangram Image as a research preview.

  • Pangram releases Image 1.0 with 99.96% accuracy in AI image detection
  • Image Flash 1.0 enables AI video detection, scoring 98.7% in DF26 study
  • Pangram integrates models into Chrome extension for real-time content flagging

More from Wednesday 4 November →