cd /news/ai-products/anthropic-launches-managed-connector… · home topics ai-products article
[ARTICLE · art-34399] src=testingcatalog.com ↗ pub= topic=ai-products verified=true sentiment=↑ positive

Anthropic launches managed connector access with Okta

Anthropic launched enterprise-managed authorization for MCP connectors through Okta, allowing administrators to centrally provision connector access across Claude chat, Claude Code, and Cowork. The feature, built on an open standard, eliminates individual user authorization and supports connectors from Asana, Atlassian, Canva, Figma, Granola, Linear, and Supabase. This positions Anthropic to meet enterprise needs for scalable, secure connector management.

read1 min views2 publishedJun 19, 2026
Anthropic launches managed connector access with Okta
Image: Testingcatalog (auto-discovered)

Anthropic has introduced enterprise-managed authorization for MCP connectors, enabling organization-wide provisioning through identity providers, beginning with Okta. This update allows administrators to centrally configure connector access, eliminating the need for individual user authorization. Upon first login, users automatically receive access to the designated connectors based on their IdP group assignments, ensuring connectors are available from the outset across Claude chat, Claude Code, and Cowork.

The feature is built on an open standard as part of the Enterprise-Managed Authorization extension to the Model Context Protocol, making it compatible with both existing and custom connectors. It is designed for enterprise customers who manage large teams and require streamlined, secure access management integrated with existing security workflows. Supported MCP providers at launch include:

  • Asana
  • Atlassian
  • Canva
  • Figma
  • Granola
  • Linear
  • Supabase

Slack integration is planned. Organizations such as Hubspot, Ramp, and Webflow are already deploying this system to their teams.

Admins benefit from unified access control, as connector permissions and revocation are administered through the trusted identity provider, minimizing the risk of lingering access. The approach also enforces separation between work and personal accounts, supporting compliance and security requirements. This positions Anthropic’s solution as a comprehensive response to the need for scalable, secure connector management in enterprise environments.

── more in #ai-products 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/anthropic-launches-m…] indexed:0 read:1min 2026-06-19 ·