Unlock Autonomous AI Agents with auth.md, Michael Grinich | MCP Night: Agent Mode Keynote
AI agents are becoming users of software — but most apps still only know how to authenticate humans.
Auth.md is an open spec for agent-native authentication: a way for AI agents to discover how to register for a service, prove identity, request scopes, receive tokens, and start using an API without breaking out of the agent workflow.
In this keynote from MCP Night: Agent Mode, WorkOS introduces Auth.md and the emerging pattern for AI agent auth standards — including agent-native signup, identity assertions, ID-JAG, delegated authorization, and service discovery through an auth.md file.
You’ll also see a live demo where an AI agent discovers that Cloudflare supports agent registration, uses an Acme identity to create an account, receives an API token and account ID, sets up the Wrangler CLI, connects to Firecrawl, and deploys a live app.
This talk covers:
Why AI agents need their own authentication and registration flows
What Auth.md is and how it helps apps become agent-ready
How agents can sign up for services, get tokens, and start using APIs
How identity proofs, scopes, entitlements, and free-tier constraints work for agents
Why “agent-ready” may become the next “enterprise-ready”
A live demo with Cloudflare, Firecrawl, ID-JAG, and agent-native deployment
Auth.md is designed to help agents become legitimate users in your system — not fake humans, not spam, and not impersonators — but real agentic users with clear identity and authorization boundaries.
Subscribe for more talks on AI agents, MCP, agent authentication, developer tools, open specs, and the future of agent-ready software.
#AuthMD #AIAgents #AgentAuth #MCP #DeveloperTools
Chapters
0:00 Why AI agents need authentication
2:36 From coding assistants to autonomous agents
7:47 What agentic systems need
18:18 Introducing Auth.md
20:58 Live demo: agent-native signup with Cloudflare
24:47 Firecrawl, ID-JAG, and API tokens
31:34 The future of agent-ready software