The broker allows autonomous agents to safely connect with multiple Model Context Protocol servers without requiring independent authentication setups for every system. Users can adjust fine-grained permissions and grant consent across integrated third-party platforms through a dedicated interface. Additionally, the platform enforces centralized verification checkpoints to approve sensitive tasks like sending emails or sharing files before execution. Zalando is currently running the open-source system internally in production across several internal servers.
Key points
The open-source broker eliminates the need for developers to build authorization servers…: The open-source broker eliminates the need for developers to build authorization servers and secure storage for each deployed MCP server.
Built-in centralized approval checks provide a final layer of enforcement before agents e…: Built-in centralized approval checks provide a final layer of enforcement before agents execute critical or sensitive actions.
Upcoming roadmap developments will target formal agent-to-agent token exchanges, intent-b…: Upcoming roadmap developments will target formal agent-to-agent token exchanges, intent-based authorization, and user-facing activity logs.
Sources checked by our analysis pipeline: 1
Agentic Identity Broker manages delegation chains for on-behalf-of flows in Agentic AI, bridges distinct OAuth2 infrastructures, and provides a secure token vault. Deployed within the call path via gateways like Agentgateway, it offloads auth burdens from both agent and MCP server creators.
For users, it provides a simple way to manage consent, granting agents granular permissions across services such as Google, GitHub, Databricks, and Linear without compromising control.
-
Secure Identity Management
Agent registration, principal authentication, and session management -
OAuth2 Delegation & Consent
Manage OAuth2 scopes and user consent for third-party service integrations -
Security-First Design
Sensitive value redaction, command injection prevention, cryptographic validation, and fail-closed architecture -
Rich Consent Experience
Modern UX for managing OAuth2 delegations with design system compliance -
Comprehensive Audit Logging
Structured JSON logging for compliance and security monitoring
Frameworks like FastMCP can implement the whole OAuth2.1 ceremonies as mandated by the MCP spec but this means that you have to configure it for every MCP Server you deploy and maintain it. You also have to configure secure storage and basically run a multitude of…
Millions of Americans voted heavily for Democrats and opposed artificial intelligence, triggering renewed regulatory battles against the technology industry. Over the next two years, congressional scrutiny will target executives, while local resistance is expected to complicate corporate plans to build new data centers. These political headwinds threaten an ecosystem already struggling to justify its massive infrastructure investments.
Chief Financial Officer Sarah Friar confirmed that the company's aggressive infrastructure roadmap will proceed uninterrupted to satisfy rising user demand. The decision follows a strong rebuke of data center projects by voters in Tuesday's midterm elections. Sustaining this momentum will depend on ongoing partnerships with major hyperscalers alongside fresh capital acquisition rounds.
The federal push to accelerate artificial intelligence infrastructure is colliding with widespread local resistance over natural resource consumption and community impact. Voters and newly elected officials across multiple states are increasingly moving to restrict or halt facility construction due to soaring electricity and water demands. This mounting regional friction poses a significant challenge to an estimated $10 trillion nationwide expansion project.