Skip to content
IAM Insights

Explainers · Glossary

Agent registry

agent registration · centralized agent registration

A single inventory of the AI agents an organisation runs, recording which agents exist, who owns each one and what it may do.

In our briefings

The claim each of the newest briefings on Agent registry would have you leave with.

  1. Visa's Eddie Onaga says that in the Visa Intelligent Commerce program an agent has to onboard through a registration process before it can interact within Visa's systems. He compares it to how Visa onboarded token requesters and mobile payment providers: there are rules to follow and data to provide. Visa can then identify those agents and audit their performance, fraud rates among other things, to hold them accountable. For merchants, whose bot screening and CDNs may block agents, he points to the Trusted Agent Protocol that Visa announced last fall with Cloudflare, through which "agents can provide their information directly to the merchants through existing rails". He describes both and shows neither.

    Visa says AI agents must register to use its agent-payment program; Stripe says its tokens can cap their spendBI-FIND-2026-2395

  2. Uber runs per-hop token exchange with a full actor chain for AI agents in production, and has published sample tokens and a latency chart. Its security token service gives each hop a fresh token scoped to one audience, with a lifetime "in the order of minutes" (both sample payloads expire 300 seconds after issue), and the token carries the attested chain from the engineer to the agent making the call. Uber says "the system has been adopted by thousands of internal agents" and reports the exchange API's P99 as "consistently below 40 milliseconds" under current load; its chart sits mostly under 10 ms, with one spike reaching 40. The post covers this identity layer. Uber frames dynamic access control and a unified policy enforcement plane as its direction on top of it, and names session and intent claims as additions the token could carry in the future.

    Uber runs per-hop token exchange with a full actor chain for AI agents in productionBI-FIND-2026-0081

  3. Mattson, SecureAuth's chief executive, argues that a model cannot be secured the way tested software is: it is non-deterministic, and a request phrased another way, or in another language, gets around whatever it was told not to do. His advice is to "just assume that it could do anything any time" and put the guardrails around the model, so that a financial transaction or a database change the agent attempts is approved and recorded. He cites Anthropic as saying no guardrail is adequate. The statement we take him to mean, Anthropic's of 12 June, which he recalls as "three weeks ago, I believe", says the company suspects perfect jailbreak resistance "is not currently possible for any model provider", while defending its own safeguards as strong. Briefings we have published on other sources move the control off the model too: a Silverfort guest calls guardrails on a probabilistic system guidance rather than control, ClearVector's John Laliberte compares them to bowling bumpers, and a zero-trust framework paper for agents adds a session-enforcement layer.

    When the model cannot be trusted, control what the agent can reach, checked on every actionBI-FIND-2026-0151

›Cited in 29 briefings

Every briefing that discusses this term, newest first.

  1. Visa says AI agents must register to use its agent-payment program; Stripe says its tokens can cap their spend

    Podcast · · Voice of MPE · Agentic commerce and payments - Is this the next commerce frontier? · Apr 7, 2026

  2. Uber runs per-hop token exchange with a full actor chain for AI agents in production

    Article · · Uber Engineering blog · Matt Mathew et al. · May 21, 2026

  3. When the model cannot be trusted, control what the agent can reach, checked on every action

    Podcast · · Tech Talks Daily · AI Agent Security: Why Identity and Access Control Matter More Than Guardrails · Aug 11, 2026

  4. When AI agents hand work to other agents, the person who started the job can get lost

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : Governing AI · Sep 7, 2026

  5. EMVCo's agent card-payment draft binds no one yet and points to a spec FIDO maintains for proof of consent

    Article · · EMVCo · Aug 27, 2026

  6. An agent-evidence draft no longer checks every actor in a delegation chain before a service admits a call

    Draft · · IETF Datatracker · Shameer Thaha et al. · Oct 19, 2026

  7. Okta and Google tie an agent's calls to the user, while GitHub's shared Copilot automations now act as Copilot

    Release tracker · · 11 vendors' release notes · Oct 2026

  8. Cisco's SD-Card rewrite pins MCP tools to what a registry signed; its security sections still read TODO

    Draft · · IETF Datatracker · Suhas Nandakumar et al. · Nov 1, 2026

  9. Raut's revised agent draft keeps token exchange out of the model's reach, and concedes the token carries no evidence of it

    Draft · · IETF Datatracker · Ashay Raut · May 22, 2026

  10. Drake's agent registry adds an opt-in brake: a registrar can block a transfer or key change until it releases it, never make one

    Draft · · IETF Datatracker · Christopher Drake, 1id.com · Sep 25, 2026

  11. Drake's revised agent registry charter makes suspensions lapse at 90 days and still bars erasing an identity

    Draft · · IETF Datatracker · Christopher Drake, 1id.com · Sep 25, 2026

  12. Cvent let staff build 6,000 agents to get them using AI; about 1,300 are in use, and agent owners never came up

    Podcast · · CXOTalk · Governing AI Agents at Scale: Identity, Scope, and Observability (with Glean and Cvent) | CXOTalk #914 · Mar 25, 2026

  13. Registering an MCP server on Bifrost ran its command, and the admin API that allowed it shipped with no password

    Article · · WorkOS Blog · Maria Paktiti · Sep 29, 2026

  14. Visa's published Trusted Agent Protocol is sample code for signed requests, with no consent record or revocation

    Article · · GitHub (visa/trusted-agent-protocol) · Visa · Oct 14, 2025

  15. Strip the agent hype and one requirement is new: the chain back to the person who started the job.

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : Secure by Design · Sep 7, 2026

  16. Cisco's SD-Card puts an A2A Agent Card in a selective-disclosure token, and leaves its registry out of scope

    Draft · · IETF Datatracker · Suhas Nandakumar et al. · Mar 2, 2026

  17. The Agent Name Service draft was rebuilt on DNS, with a GoDaddy author, and no standards body has adopted it

    Draft · · IETF Datatracker · Scott Courtney et al. · Apr 13, 2026

  18. MCP made authorization optional, and two identity veterans say most servers took the option

    Podcast · · Hybrid Identity Protection Podcast · Agentic AI and the Authorization Gap No One Closed · Jun 9, 2026

  19. Google's agent registry went GA in June while Okta, SailPoint and Ping pulled agents into their own lists

    Release tracker · · 11 vendors' release notes · Jun 2026

  20. Microsoft and Google made AI agent identity generally available in April; Okta's notes put its GA in May

    Release tracker · · 8 vendors' release notes · Apr 2026

  21. A Huawei agent draft keeps one 'master agent' as gatekeeper and drops the line that had servers re-check it

    Draft · · IETF Datatracker · Yuan Ni et al. · Feb 28, 2026

  22. A January design paper argued AP2 and x402 move money before anyone checks the work, and proposed escrow

    Paper · · arXiv · Mehul Goenka et al. · Jan 30, 2026

  23. A DeepMind paper puts agent markets on DIDs and credentials but leaves delegation unspecified

    Paper · · arXiv · Nenad Tomašev et al. · Sep 12, 2025

  24. The July 2025 Cross App Access draft lets the IdP decide app-to-app access and treats agents as plain clients

    Draft · · IETF Datatracker · Aaron Parecki et al. · Jul 2, 2025

  25. A survey of MCP and A2A attacks pairs each identity threat with a fix, and tests none of them

    Paper · · arXiv · Mohamed Amine Ferrag et al. · Jun 29, 2025

  26. The first Agent Name Service paper puts capabilities in the name and leaves protocol translation and governance out

    Paper · · arXiv (cs.CR preprint 2505.10609) / OWASP Agentic Security Initiative · Ken Huang et al. · May 15, 2025

  27. A 'zero trust' registry against AI tool squatting still has to trust its administrator

    Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 28, 2025

  28. An early MCP security checklist was never tested, and the protocol has since adopted only part of it

    Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 11, 2025

  29. MAESTRO names your AI agents' identity threats and leaves designing the controls to you

    Article · · Cloud Security Alliance · Ken Huang · Feb 6, 2025

Related terms

What appears alongside Agent registry in the same briefings.

SD Agent (SD-Card)ANS