Radar / AI security / Agentic Identity Broker
Agentic Identity Broker: OAuth delegation for AI agents
MIT-licensed OAuth2 broker from the Zalando Incubator that lets a user give an AI agent scoped, revocable access to MCP services without ever handing over raw credentials.
Why it matters
Solves the agent-identity gap in corporate environments: agents never see user tokens, delegation is per user, per agent, and per service, and approvals and audit logs are centralized.
What you could build with it
A platform team running coding agents against GitHub, Jira, and internal tools could put this broker between agents and services so each agent acts with the requesting user's own scoped permissions, revocable at any time.
Does it hold up?
Running in production at Zalando across hundreds of agents and dozens of MCP servers, but v0.1 and focused on on-behalf-of flows — early adopters should expect rough edges outside that path.
Built with Agentic Identity Broker
- Agent Security & Identity (Part 1): Who Are You, Who's Your Agent, And What Should They Be Allowed?hackernoon · A practitioner adopts AIB for a Kubernetes agent platform instead of building identity plumbing, walking through delegation, consent, and proxy mode.
- Agentic Identity Broker on HN Showcasearticle · Mirror of the Show HN post by co-author Jan, with the v0.1 production status and local try-out steps.
Learn more
First spotted on github: source.
More AI security
NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Cloudflare security-audit-skill: turn your coding agent into a security auditorA coding-agent skill for multi-phase security audits with independently verified, machine-readable findings.security · JEV 0.72Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71AiSOC: open-source AI security operations center with agent triageSelf-hosted SOC that fuses alerts into incidents and hands them to LLM agents that record every prompt and tool call…security · JEV 0.71iFixAi: independent auditing of AI agents in under 120 secondsiFixAi audits whether an AI agent is doing what it is supposed to do, run by a human or by the agent itself, answering…security · JEV 0.68sapper-v2: autonomous pentest legion with an AI commander and worker swarmsapper-v2 is an autonomous penetration-testing system: an AI commander directs a worker swarm over a layered…security · JEV 0.6
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.