Skip to content
IAM Insights

Explainers · Glossary

OAuth Token Exchange

token exchange · RFC 8693 · RFC 8693 OAuth Token Exchange · RFC 8693 OAuth 2.0 Token Exchange

By Boston Identity · Explained · 7 min read

The short answer

Token exchange is an OAuth standard, RFC 8693, that lets a service trade a token it holds for a new token meant for the next service, either posing as the user or openly acting on the user's behalf.

What it is
A protocol
Defined by
IETF, RFC 8693 (Standards Track, 2020)
Who it's for
Teams wiring services and agents to APIs
In our briefings
113By month of the source: 2025-12: 1, 2026-01: 0, 2026-02: 7, 2026-03: 8, 2026-04: 6, 2026-05: 8, 2026-06: 8, 2026-07: 14, 2026-08: 4, 2026-09: 19, 2026-10: 18, 2026-11: 22by month, last 12
01

What is OAuth Token Exchange?

A front-end service gets a call carrying a user's access token and must call a back-end service for that same user. Token exchange is the standard way to get a credential for that second call: the service sends the token it holds to an OAuth authorization server and gets back a new one fit for the back end.§1 OAuth is the web's common framework for letting one application act at another without sharing passwords. RFC 8693, published by the Internet Engineering Task Force (IETF) in January 2020, lets its authorization server act as a security token service (STS), which checks the tokens it is given and issues new ones.§1 The new token might be scoped more narrowly for the downstream service, or be a different kind of token altogether.§1

The RFC separates two ways one party can act for another.§1.1 Under impersonation, service A gets a token that still names user B, and anyone receiving it is in effect dealing with B. Under delegation, A keeps its own identity and the token says A acts for B; in the RFC's words, "In a sense, A is an agent for B".§1.1 Which of the two a deployment issues is left to policy at the authorization server.§1.1

Not the same as forwarding the user's own token to the next service. In an exchange the authorization server checks the token it is handed and issues a new one under the policy for the service the client names.§2.3

02

How does OAuth Token Exchange work?

The RFC's worked example has a front service holding a user's access token, an authorization server acting as the STS, and a back-end service the front service needs to call.§2.3 Whoever asks for the exchange is called the client, even when it is itself a server.§1

Figure steps
  1. A call reaches the front service with a token
  2. The client asks the authorization server for a new token
  3. The client adds an actor token to ask for delegation
  4. The authorization server checks the tokens and applies policy
  5. The authorization server returns the new token
  6. The front service calls the back end
Fig. 1

The front service hands the user's token to the authorization server as subject_token, adds an actor_token only when it wants delegation, and calls the back end with the token it gets back.

Drawn from RFC 8693, sections 2 and 4

Swipe for the full figure →

  1. A call reaches the front service with a token

    A request arrives at the front service with the user's OAuth access token in its Authorization header.§2.3 To reach the back end, the front service takes the client role and trades that token for one suited to the backend call.§1

  2. The client asks the authorization server for a new token

    The client posts to the authorization server's token endpoint with grant_type set to the token-exchange value.§2.1 It must send subject_token, a token for the party the request is made for, and subject_token_type, which says what kind of token that is.§2.1 It may name the target as a resource address or as an audience, a logical name for the service the token is for, and may ask for a scope and a token type (requested_token_type).§2.1 If the server requires it, the client authenticates the normal OAuth way.§2.1

  3. The client adds an actor token to ask for delegation

    For delegation, the client also sends actor_token, a token for the party that will act, with actor_token_type.§2.1 The actor token is optional, but without it delegation is impossible.App. A.1.1 A may_act claim inside the subject token can name who may act for the subject, and the server can use it to decide whether to allow the request.§4.4

  4. The authorization server checks the tokens and applies policy

    The server must validate the subject token, and the actor token if there is one, by the rules for each token type.§2.1 In the RFC's example it reads the resource parameter to pick the policy for the target.§2.3 An invalid or unacceptable token must get the invalid_request error; a target the server will not issue for should get invalid_target.§2.2.2

  5. The authorization server returns the new token

    A successful reply carries the new token in access_token, with issued_token_type and token_type, and should give its lifetime in expires_in.§2.2.1 The name access_token is historical: the issued token need not be an OAuth access token.§2.2.1 If the scope granted differs from the scope requested, the reply must include it.§2.2.1 In a delegation issued as a JSON Web Token, sub names the user and an act claim names the acting party, nesting to show earlier actors.§4.1

  6. The front service calls the back end

    The front service presents the new token to the back-end service, and in the RFC's example that token is valid for one minute.§2.3 Unless the token type has its own rules, such as one-time use, the exchange does not change whether the original tokens are valid. Renewing the input token is not expected to extend the new one, and passing on a revocation is left to each implementation.§2.1

03

Why does OAuth Token Exchange matter now?

Most of the agent delegation designs we have read come down to this one grant type.1 The Model Context Protocol (MCP) now has an enterprise login extension in which an employee's AI client uses token exchange to trade the single sign-on token from the identity provider for an assertion the MCP server's own authorization server accepts.2 The OAuth identity-chaining draft crosses into another company's domain by running an RFC 8693 exchange first and presenting the result there as a signed grant.3

Uber gives every agent hop a fresh token for one audience that lives five minutes, across thousands of internal agents, and reports that 99 percent of exchanges finish in under 40 milliseconds.4 Auth0's Agent Gateway, in beta, uses token exchange to reach the software company's own APIs and MCP tools.5 In June, Okta moved its agents' requests to Salesforce and MCP servers onto OAuth token exchange.6

At the Identiverse conference in June, practitioners settled on delegate, never impersonate: the agent gets its own identity, and the person's authority passes to it by token exchange at each hop.7 MCP's core authorization specification, as of its 28 July 2026 revision, still has no token exchange and no actor claim.8 One forecast we track says it gains a delegated-identity mechanism, such as a token-exchange profile, by September 2027.9

04

Where does it fit?

Compared withHow OAuth Token Exchange differs
Security Token ServiceA security token service is the role: a service that checks tokens and issues new ones. Token exchange is the OAuth protocol for asking one; web services used the older WS-Trust protocol for the same job.§1
Transaction TokensA transaction token is minted once, when a request comes in at the external-facing endpoint, and carried unchanged down the internal chain with no actor chain. Uber's token exchange issues a fresh token at every hop instead.10
OAuth Identity and Authorization Chaining Across DomainsIdentity chaining is built on token exchange: the client exchanges its token for a grant addressed to one authorization server in another domain, then presents it there for a local access token.3
OAuthOrdinary OAuth trades a person's approval for an access token. Token exchange adds a grant type that takes a token in and gives a different token back.§1
05

What goes wrong?

Narrowing is not automatic. Nothing in the RFC requires the new token to carry less authority than the old one, and its security section only suggests the scope claim and short lifetimes to limit abuse.§5,11 Karl McGuinness says that in production deployments today, child tokens routinely inherit the parent's full scope unless someone narrows them on purpose.12 The RFC also leaves the tokens' format, their security properties and the trust model to profiles and to each deployment, including whether tokens are signed, encrypted or bound to a key.§1 Client authentication is a deployment choice too, and the RFC warns that leaving it out lets anyone holding a compromised token turn it into other tokens.§2.1

Impersonation hides the agent: whoever receives the token is dealing with the user.§1.1 Delegation records the agent, but for access decisions a consumer must look only at the top-level claims and the current actor, and earlier actors in nested act claims are informational only.§4.1 Ashay Raut of Amazon says an implementer may keep the actor chain in the token or drop it,13 and George Fletcher says implementers already put the user and the agent the wrong way round between sub and act.14

Raut also argues that an exchange for every sub-agent would slow the whole job,15 and no shipping standard carries the original person and the limits added along the way through a chain of agents.16

06

What should a security leader ask?

  1. 01

    When our services or agents exchange a token, does the authorization server narrow the scope and audience, or can the new token do everything the old one could?

  2. 02

    Which of our agents act as the user rather than as themselves on the user's behalf, and can our logs tell the two apart?

  3. 03

    Does our token endpoint require client authentication for token exchange, and which clients may exchange which users' tokens?

  4. 04

    Are the tokens our exchange issues signed, encrypted or bound to the holder's key, or are they plain bearer tokens?

  5. 05

    For a vendor: does your exchanged token name the user in sub and the agent in act, and do you keep or drop the earlier actors?

07

Sources

›Evidence: 16 claims from 13 briefings
  1. 1BI-FIND-2020-0004 · The token exchange RFC that agent designs cite says its record of earlier actors is not for access decisionsEvery delegation design in this corpus reduces to one grant type from a January 2020 RFC written for services, by engineers at Microsoft, Ping Identity, Yubico and Visa, that never mentions an agent. The standard defines an HTTP and JSON security token service: a client posts a subject token and, optionally, an actor token to the token endpoint and receives a new token for a named audience, with typed token identifiers so a SAML assertion can be traded for a JWT. The transaction-tokens draft mints its token through this exchange, the identity-chaining draft runs it before a JWT bearer grant to cross domains, Uber's exchange is conceptually based on it and its builder says the newer standards are not ready to implement as written, and the working group's agent draft composes it rather than replacing it. The agent-specific work is all profile; the base has not changed in six years.
  2. 2BI-FIND-2026-0678 · MCP's enterprise login extension says IdP revocation is immediate. Its own spec does not back that upMCP now has a stable way for a company's identity provider to stand between an employee's AI client and every MCP server. The client trades the employee's single sign-on ID token at the IdP for an ID-JAG, using OAuth token exchange, and hands that to the MCP server's own authorization server as a JWT assertion; the IdP checks group, role and conditional-access policy before issuing, and the employee sees one corporate login instead of a consent screen per server. The ID-JAG must be addressed to that authorization server, and when the client names a resource the access token must be restricted to it. The extension is opt-in: a server signals support in its authorization-server metadata.
  3. 3BI-FIND-2026-0185 · The cross-domain OAuth draft is one step from an RFC, and it never mentions agentsChaining defines no new token. A client in domain A takes the token it already holds to its own authorization server and, through RFC 8693 token exchange, receives a signed JWT grant whose audience is one authorization server in domain B; it presents that grant there under RFC 7523's JWT-bearer profile and gets a domain-B access token. The precondition is arranged in advance: B trusts A's signing keys, typically through A's published key set. The audience 'is restricted to a single authorization server in trust domain B to prevent an authorization server from presenting the client's authorization grant to an authorization server in a different trust domain', so a grant cannot be relayed on to a domain C. Uber's production exchange is 'conceptually based on' the first of those RFCs; ZeroID's delegation engine is built on it; the draft shows what the second RFC adds when the far end is someone else's server.
  4. 4BI-FIND-2026-0081 · Uber built the delegation chain the rest of the field calls unsolvedA large enterprise has per-hop token exchange with a full actor chain running in production for AI agents, and has published the numbers and the tokens. At Uber every agent hop takes a fresh audience-scoped token that lives five minutes (the two payloads in the post expire 300 seconds after issue) and carries the attested chain from the engineer down to the current sub-agent, each entry with its own issue time. Thousands of internal agents use it, and Uber reports a P99 of under 40 milliseconds on the exchange API even when one task makes dozens of tool calls; its own chart runs mostly under 10 ms, with one spike touching 40. Multi-hop delegation is no longer only a whiteboard problem.
  5. 5BI-FIND-2026-0265 · Auth0's agent gateway keeps every credential away from the agent; the post shows no step where a person approvesIn Auth0's Agent Gateway design the agent never holds a credential that works anywhere but the gateway. It receives one short-lived token the gateway alone accepts; the gateway then checks policy before each tool call and obtains the real credential itself, from Token Vault for a customer's outside accounts such as Slack or Teams, and by token exchange for the software company's own APIs and MCP tools. Each call is tied to an agent, a customer organization and a user, so an agent working for one customer cannot use another's connection. A kill switch disables an agent or cuts its downstream access. The product is in beta by application, with no price or date.
  6. 6BI-FIND-2026-1188 · Google's agent registry went GA in June while Okta, SailPoint and Ping pulled agents into their own listsCloudflare and Okta both shipped ways in June for an agent or bot to authenticate with no person in the loop. Cloudflare's temporary accounts (June 19) let an agent with no Cloudflare credentials deploy Workers to a temporary preview account, with no sign-up, browser login or API token. A week later its MCP server portals accepted Access service tokens, so autonomous agents reach upstream MCP servers without a browser OAuth flow; the setup turns per-user authorization off, and the portal then uses the admin credential instead of a per-user grant. Okta's agent-to-agent connections, in early access in preview from June 17, let service apps call AI agents without user context, and its Auth0 unit made machine-to-machine access for third-party apps generally available on June 2 for callers that run without a user. In the same month Cloudflare shipped OAuth clients that act for a user after consent, and Okta moved its agents' requests to Salesforce and MCP servers onto OAuth token exchange, so the no-user routes sit beside delegated ones.
  7. 7BI-FIND-2026-0469 · Eight panels agree an agent acts for a person, never as that person. When agents hand work to other agents, nobody had an answer.Across its eight panels the summit settles one rule and names one unsolved problem. The rule is to delegate, never impersonate: an agent gets its own identity, the person's authority passes to it by token exchange (an OAuth step that swaps one token for another) at each hop from one party to the next, and the agent may do only what every identity in the chain is allowed to do. The unsolved problem is the second hop. Once an agent starts other agents, no shipping standard carries the person who started the job and the limits added along the way. An Amazon engineer works on the transaction-token draft, a draft standard for short-lived tokens that carry a request's context between services. He says the record of the chain is optional and survives only if the HTTP header has room. His own group is drafting a way for a parent agent to issue its children's identities, the opposite of the rule every other panel states. Uber built its own record of the chain and published it; nobody on the stage had built one.
  8. 8BI-FIND-2026-0189 · MCP's authorization spec makes the agent a plain OAuth client and leaves delegation to an extensionAs of the 28 July 2026 revision, an MCP client is an OAuth 2.1 client and an MCP server is an OAuth 2.1 resource server, and that is the whole identity model. Authorization is optional; HTTP transports SHOULD use it, and 'implementations using an STDIO transport SHOULD NOT follow this specification, and instead retrieve credentials from the environment'. The authorization server is out of scope. There is no actor claim, no on-behalf-of flow, no token exchange and no transaction-token profile: nothing in the token says whom the agent is acting for, which is what the Identiverse summit panel meant by 'not a policy system' and what WorkOS meant by the gateway being undefined. Anything of that kind is routed to the new extension model, optional and additive, in a separate repository. This page is the baseline against which the summit's forecast, that the specification gains a delegated-identity mechanism within a year, will be graded.
  9. 9BI-CALL-2026-0036 · The rules cover one agent acting for one person; they break when that agent hands work to other agentsWithin 12 months the Model Context Protocol's authorization specification gains an explicit delegated-identity mechanism: a token-exchange profile, an actor or on-behalf-of claim, or a transaction-token profile, so that a downstream MCP server can see both the calling agent and the user it acts for. It settles wrong if, by September 2027, the specification still models the client as a plain OAuth client with no delegation element.
  10. 10BI-FIND-2026-0171 · OAuth's transaction token goes unchanged down a service chain and names who started it, not who acted in betweenA transaction token is minted once, at the edge, and carried unchanged down the chain. The external-facing endpoint trades the inbound access token at the transaction token service for a short-lived JWT whose subject is the user or workload that started the transaction, whose req_wl claim names the workload that asked for it, and whose txn claim is the transaction's own identifier; every later workload forwards the same token in a dedicated Txn-Token header and verifies the signature itself. There is no actor chain. Uber's production design re-exchanges at every hop and grows an act_chain of user, on-call agent and investigation agent; ZeroID intersects scope at each delegation. The OAuth group chose the other design: one token, one transaction, and a replacement path it explicitly warns 'potentially negates the primary purpose'. For agents that spawn agents, this draft attributes the transaction to its initiator and says nothing about who acted in the middle.
  11. 11BI-FIND-2020-0002 · The token exchange RFC that agent designs cite says its record of earlier actors is not for access decisionsThe two controls the agent designs lean on hardest, narrowing authority at each hop and controlling who may perform an exchange, are both left to the authorization server's discretion by the RFC. Nothing in it requires the issued token's scope to be a subset of the subject token's: scope in the request is optional and service-defined, the response rule only says when scope must be echoed back, and the security section suggests scope as an abuse mitigation without a normative keyword. Client authentication at the token endpoint is likewise a deployment decision, with the RFC noting only that omitting it lets anyone holding a stolen token launder it into more tokens. McGuinness's reading that token exchange supplies the plumbing and not the constraint is the text; Highflame's attenuation by intersection and Uber's rule that only its security token service may issue an agent token are policies those deployments added on top.
  12. 12BI-FIND-2026-0228 · Containing an agent is not a backup to defining its task; where the agent cannot see everything, it comes firstA delegated mission's child authority must be a subset of the parent's, and nothing in the token plumbing makes it so. McGuinness's reading is that OAuth token exchange, RFC 8693, carries a delegated token from one party to the next but leaves the narrowing to the implementation, and that in production exchange deployments today child tokens routinely inherit the parent's full scope unless someone explicitly attenuates them. He adds two things the corpus had not said: delegation degrades governability, because a child runs on a different runtime with weaker telemetry, so each hop needs its own trust-quality rating and a tighter budget regardless of its nominal bounds; and a sub-agent spawned at runtime has no clear issuer of child authority at all. Uber's production chain carries who asked through every hop and does not describe narrowing; Highflame's open-source layer makes attenuation by intersection an explicit feature, which is what a default would not need.
  13. 13BI-FIND-2026-0239 · Keeping an agent's delegation chain is optional, and room in the HTTP header decides whether it survivesThe record of who delegated to whom is optional in practice, and what decides whether it survives is room in the HTTP header. Amazon principal engineer Ashay Raut, who works on the OAuth transaction-token draft, says an implementer doing token exchange may keep the actor chain in the token or drop it, and that a bank or a hospital that needs it should keep it somewhere else and decide for itself where. That matches the text: RFC 8693 treats earlier actors as informational only. Uber carries the full chain in every token; nothing obliges the next implementer to.
  14. 14BI-FIND-2026-0512 · Transaction tokens are nearly a standard, and there is still no agreed place in them for the agentFletcher's rule for agents is not to hand them the user's credentials or access token, and to keep the agent's authentication apart from the authorization it carries. Where the agent then appears in a transaction token is open: the token can carry it, but "there is no profile that says we're going to call that claim X", and when a gateway rather than the agent requests the token the original caller has no standard place. He points to Ashay Raut's agents draft, which adds an actor chain and agent context, says Karl McGuinness's actor proposal probably needs merging with it, and notes that implementers already put the user and the agent the wrong way round between sub and act.
  15. 15BI-FIND-2026-0242 · Keeping an agent's delegation chain is optional, and room in the HTTP header decides whether it survivesStandards work is under way to let an agent hand identities to the sub-agents it spawns without going back to a central issuer each time. Raut describes it as work his group is doing, with agents treated as workloads, and gives the reason plainly: a round trip to an authority service and a token exchange for every sub-agent would slow the whole job. That runs against the rule the rest of this corpus treats as settled. Uber lets only its token service mint an agent token, and an earlier panel at the same summit said an agent should never mint its own credentials.
  16. 16BI-FIND-2026-0070 · The rules cover one agent acting for one person; they break when that agent hands work to other agentsAgents that spawn agents are the unsolved problem. Once an orchestrator hands work to sub-agents, the identity of the person who started the job is lost, separation-of-duties rules are broken by accident, and no shipping standard carries the original actor and the accumulated constraints through the chain. Every technical source in this corpus that models multi-agent systems says the same.

›In our briefings

The claim each of the newest briefings on OAuth Token Exchange would have you leave with.

  1. 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

  2. Auth0 Agent Gateway, badged 'Beta Now' on its slide, is one hub between an organisation's agents and the MCP servers they call. Auth0 says it can handle access policies, credential injection, audit logging and organisation boundaries, and the slide adds a kill switch. The console in the demo already lists Asana, Atlassian, BambooHR, GitHub, Notion, Salesforce, Sentry, Slack and Workday as servers, counts '31 of 200 tools max', and labels MCP Servers beta and a separate Agents section preview. One HR agent, with the same code and one deployment, reaches Workday and Slack for one customer tenant and BambooHR and Slack for another, because the gateway handles the token exchanges and routes the agent to the right tool for each customer. Our briefing on WorkOS's account of Sierra's internal gateway found that access control and audit held up that rollout, and we read Agent Gateway as a product for that layer. The keynote does not mention Ping Identity, but our briefing on Ping's March 2026 launch video covers a Ping product also called Agent Gateway.

    Auth0 ships an agent gateway in beta and moves the identity form into the chat so the agent never sees the cardBI-FIND-2026-0214

  3. Asked which identity and security controls are most likely to break first as agentic systems scale, John Yeoh, CSA's chief scientific officer, names lifecycle management. He cites CircleCI and Microsoft's Midnight Blizzard breach as poor lifecycle management of non-human identities, where keys for secrets were not rotated fast enough, and expects agents to fail faster because people now give them specs that spin up sub-agents. Access reviews that ignore intent and behaviour come next, then logging, in what he calls "a good domino of control collapse". Aizome's Amir Ofek answers the same question differently: applying controls built for non-human identities, which are deterministic rather than dynamic, is what will break first.

    CSA's John Yeoh expects lifecycle management to be the first agent control to breakBI-FIND-2026-0113

›Cited in 113 briefings

Every briefing that discusses this term, newest first.

  1. 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

  2. Auth0 ships an agent gateway in beta and moves the identity form into the chat so the agent never sees the card

    Video · · Okta · Uploaded September 24, 2026

  3. CSA's John Yeoh expects lifecycle management to be the first agent control to break

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : The Next 24 Months · Sep 7, 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. Asor's agent-chain draft now says a chain keeps verifying after its principal leaves, until expiry or revocation

    Draft · · IETF Datatracker · Rafael Asor · Oct 28, 2026

  6. Transaction Tokens carry who started a request through internal services and define no list of the hops in between

    Draft · · IETF OAuth Working Group · Atul Tulshibagwale et al. · Jul 30, 2026

  7. OAuth's draft for crossing trust domains is approved for publication and never says agent

    Draft · · IETF OAuth Working Group · Arndt Schwenkschuster et al. · Jul 19, 2026

  8. A new STIR draft would let a number's holder require AI agents calling from it to say so

    Draft · · IETF Datatracker · Jon Peterson, TransUnion · Nov 2, 2026

  9. OAuth token exchange does not guarantee a sub-agent stays inside its parent's access

    Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 18, 2026

  10. An agent-mandate draft checks who may delegate, and now intends to carry its chain in Asor's format

    Draft · · IETF Datatracker · Claudiu Hulea, Braincap SRL · Oct 24, 2026

  11. Agent-audit draft now admits a call on the principal and the current agent, as RFC 8693 requires

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

  12. 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

  13. 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

  14. Register a platform's identity provider once, not each agent: trust rests on its issuer, with no revocation

    Draft · · IETF Datatracker · Paul Carleton et al. · Sep 22, 2026

  15. An OAuth draft lets the API, not the agent, describe the approval, and now name the key the token is bound to

    Draft · · IETF Datatracker · Yaroslav Rosomakho et al. · Jun 25, 2026

  16. WIMSE's agent draft adds how an agent's access ends and where policy engines fit, without a new requirement

    Draft · · IETF WIMSE Working Group · Pieter Kasselman et al. · Sep 15, 2026

  17. OAuth's URL client ID draft tightens server rules in -03; the client is still whoever controls the URL

    Draft · · IETF Datatracker · Aaron Parecki et al. · Jul 6, 2026

  18. WorkOS's agent checklist limits a delegated agent to what it and its user may both do, checked on every call

    Article · · WorkOS Blog · Maria Paktiti · Sep 30, 2026

  19. 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

  20. An agent audit draft says the agent is not trusted, yet lets the agent's operator run the audit store

    Draft · · IETF Datatracker · Mirja Kühlewind et al. · Sep 7, 2026

  21. 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

  22. OAuth's draft for token requests that wait on a person now gives the client a link for the user to approve

    Draft · · IETF Datatracker · Guilherme de Oliveira Niero et al. · Sep 23, 2026

  23. Sweeney's delegation draft concedes its server is trusted with users' credentials, and drops an interop claim

    Draft · · IETF Datatracker · Kieran Sweeney · Oct 13, 2026

  24. Cross-App Access draft warns that one stolen sign-in token could reach every app the identity provider permits

    Draft · · IETF Datatracker · Aaron Parecki et al. · May 21, 2026

  25. RFC 9207's issuer check stops at the redirect, and n8n's token-exchange flaw sat just past it

    Article · · WorkOS · Maria Paktiti · Jul 20, 2026

  26. IETF workload practices draft describes single-audience JWTs in place of stored secrets and discourages token exchange

    Draft · · IETF Datatracker · Arndt Schwenkschuster et al. · Sep 22, 2026

  27. Lee's draft would hold an agent's action at the boundary until a receipt for that exact action passes every check

    Draft · · IETF Datatracker · Yong Bok Lee, Meridian Verity Group · Jun 5, 2026

  28. Agent URI draft -04 ties an agent's name to a key document and bars OAuth servers from trusting the name alone

    Draft · · IETF Datatracker · Yaswanth Narvaneni et al. · Oct 20, 2026

  29. Agent delegation records not anchored in trusted time become deniable once timestamps can be forged

    Draft · · IETF Datatracker · V.K. Uppalapati · Sep 29, 2026

  30. Niyikiza's agent tokens narrow to a tool's arguments offline; revision -02 breaks -01 implementations

    Draft · · IETF Datatracker · Niki Aimable Niyikiza · Jun 15, 2026

  31. OAuth tokens prove an agent's rights, not a person's consent; revision 05 adds a day-long grant with spend caps

    Draft · · IETF Datatracker · Meiling Chen et al. · Oct 27, 2026

  32. A cross-domain transaction-token grant now names AI agents as a use and keeps the call chain at home

    Draft · · IETF Datatracker · George Fletcher et al. · Sep 10, 2026

  33. Five places to put authorization in microservices, and why Drus says the classic gateway one does not scale

    Video · · OWASP Foundation · Uploaded October 21, 2026

  34. Barclays mandates one gateway for its agents' budgets, blocks and audit, and its AI engineering director says the setup is not yet tested at scale

    Podcast · · Insecure Agents · The Fishbowl Problem: Agent Identity Across Clouds and Vendors, with Andy McMahon (Barclays) · Oct 5, 2026

  35. Delegation receipts for AI agents, revision 15: holding a copy of a receipt no longer lets you extend the chain

    Draft · · IETF Datatracker · Ryan Nelson, Authproof · Oct 22, 2026

  36. Agents would show a signed user goal with each OAuth scope request; the draft leaves open how the server checks it

    Draft · · IETF Datatracker · Meiling Chen et al. · Oct 19, 2026

  37. SaaS apps that only know users end up giving agents human accounts, says Okta's former chief architect

    Podcast · · The Identity Jedi Show: Where Identity Meets Strategy · Agents need a mission, not a key. · Oct 21, 2026

  38. ChainIT's design has the payment rail rebuild each payment's hash before money moves; the paper reports no test

    Paper · · arXiv · Jeremy Blackburn et al. · Oct 16, 2026

  39. An individual IETF draft takes a workload's role and group out of its name and puts them in separate metadata

    Draft · · IETF Datatracker · Shlomo Zalman Heigh et al. · Oct 16, 2026

  40. Six companies' agent-auth draft, since adopted by the WIMSE group, keeps credentials out of the model's reach

    Draft · · IETF Internet-Draft (individual submission, since adopted by the WIMSE working group) · Pieter Kasselman et al. · Jul 6, 2026

  41. Auth0 says its agent checkout token is limited to one purchase and amount; the tokens in its own diagram carry neither

    Article · · Auth0 Blog · Sep 28, 2026

  42. An OAuth agent profile has the token server block any widening of scope, and leaves revoking the chain optional

    Draft · · IETF Datatracker · Sanjeev Kumar, Orchestrum Technologies LLP · Aug 30, 2026

  43. An OAuth profile for AI agents makes every hand-off cut privileges, but a shorter expiry alone counts as a cut

    Draft · · IETF Datatracker · Angel Cruz · Feb 7, 2026

  44. Anthropic asks for per-agent identity; its guide leaves Claude Code sub-agent credentials unspecified

    Article · · Anthropic (Claude) · Anthropic · May 27, 2026

  45. Anthropic says agents should never use static API keys, yet its sub-agents can carry the parent's permissions

    Article · · Anthropic · Anthropic · May 18, 2026

  46. Human Delegation Provenance is now an audit record only, and one that cannot prove it is complete

    Draft · · IETF Datatracker · Asiri Dalugoda, Helixar · Oct 6, 2026

  47. The PEDIGREE draft has verifiers re-check every ancestor of an agent's token, without saying how to fetch them

    Draft · · IETF Datatracker · Karthik Rampalli, Glyphzero Labs · Apr 25, 2026

  48. OpenA2A's draft aims to keep secrets from the agent, and says no implementation yet supports its new controls

    Draft · · IETF Datatracker · Abdel Fane, OpenA2A · Oct 2, 2026

  49. Two implementations stop at the last of Reece's ten cross-company rules: a person approving one specific action

    Draft · · IETF Datatracker · Morgan Reece · Aug 31, 2026

  50. A2A 1.0 connects agents across companies and leaves out the person they act for

    Article · · A2A Protocol (Linux Foundation) · A2A Protocol project et al. · May 28, 2026

  51. Three vendors now route MCP tool calls through an identity check, and only Cloudflare's is generally available

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

  52. OWASP's agent Top 10 blames identity systems built for people, and does not say how it chose or ranked its risks

    Article · · OWASP GenAI Security Project · John Sotiropoulos et al. · Dec 9, 2025

  53. NIST's agent identity work starts from OAuth, SPIFFE and SCIM and defers agents from outside the enterprise

    Article · · NIST National Cybersecurity Center of Excellence · Harold Booth et al. · Feb 5, 2026

  54. MCP's enterprise login extension says IdP revocation is immediate. Its own spec does not back that up

    Article · · Model Context Protocol (modelcontextprotocol.io) · MCP project et al. · Jun 18, 2026

  55. A draft ties what each AI agent may read to what it may do, and still can't take a grant back

    Draft · · IETF Datatracker · Hamdy Atakora · Sep 21, 2026

  56. PayPal moved MCP tool permission checks into the server, and prompt-injected agents stopped getting through

    Paper · · arXiv · Huan Li et al. · Sep 18, 2026

  57. Coetzee's agent token is good for one declared call, and the hard part is hashing that call the same way twice

    Draft · · IETF Datatracker · Rudolf Jacobus Coetzee · Jul 19, 2026

  58. A SANS instructor's broker vaults agents' real keys, but its third delivery model breaks the abstract's promise

    Draft · · IETF Datatracker · Kenneth G. Hartman · Mar 29, 2026

  59. Transaction tokens are nearly a standard, and there is still no agreed place in them for the agent

    Podcast · · Identity at the Center · #449 - Decoded - Transaction Tokens with George Fletcher · Sep 21, 2026

  60. A draft token hides some claims, works with old servers unchanged, and leaves agent delegation claims visible

    Draft · · IETF Datatracker · Su-hyeon Forten Lee · Oct 3, 2026

  61. 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

  62. Eight panels agree an agent acts for a person, never as that person. When agents hand work to other agents, nobody had an answer.

    Conference · · Las Vegas · June 2026, a one-day summit track inside Identiverse 2026; the eight panels were published as podcast episodes between 18 August and 7 September 2026

  63. A third SCIM agent draft gives the agent five lifecycle states, a quarantine, and an archive it can never leave

    Draft · · IETF Datatracker · Saurabh Kushwaha, Oracle · Jul 27, 2026

  64. OAuth handles an agent in one company, working while you watch. The OpenID paper says that is where it stops.

    Article · · OpenID Foundation · Tobin South et al. · Oct 2025

  65. The IETF's workload-identity architecture gives AI agents one subsection, calling an agent a delegated workload

    Draft · · IETF Datatracker · Joseph Salowey et al. · Jul 6, 2026

  66. The 'intent' in the Agentic JWT draft is a workflow step, and the agent reports its own fingerprint

    Draft · · IETF Datatracker · Abhishek Goswami · Jul 1, 2026

  67. 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

  68. The IBAC paper's strict mode blocked every prompt injection, and its agent finished only a third of its tasks

    Article · · ibac.dev · Jordan Potti · Mar 3, 2026

  69. Auth0's agent gateway keeps every credential away from the agent; the post shows no step where a person approves

    Article · · Auth0 Blog · Andrés Aguiar · Sep 18, 2026

  70. Keeping an agent's delegation chain is optional, and room in the HTTP header decides whether it survives

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : The New NHI Risk Reality · Aug 26, 2026

  71. Mission-Bound OAuth's author now says the mission object does not belong in OAuth

    Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 15, 2026

  72. Most of the work in Sierra's MCP gateway was identity: who each agent acts as and what it may reach

    Article · · Sierra Engineering · Mihai Parparita · Jul 22, 2026

  73. MCP's authorization spec makes the agent a plain OAuth client and leaves delegation to an extension

    Article · · Model Context Protocol project · Jul 28, 2026

  74. An MCP gateway can be demoed in a week; Sierra's rollout waited on the auth layer underneath it

    Article · · WorkOS Blog · Maria Paktiti · Sep 11, 2026

  75. Highflame's open-source ZeroID narrows an agent's token at every hop, a step we did not find in Uber's write-up

    Article · · Highflame (GitHub) · Sep 25, 2026

  76. SailPoint's product chief wants an agent's access checked before each tool call and again at each resource access

    Podcast · · The Security Strategist · Who Owns an AI Agent? Rethinking Identity, Security, & Accountability · Aug 27, 2026

  77. IPC passes a delegation chain between services; its signature proves only the last signer

    Draft · · IETF Datatracker · Ravi Kant Sharma, Ericsson · Jul 23, 2026

  78. A July OAuth draft keeps agent identity stable as keys rotate

    Draft · · IETF Datatracker · Karl McGuinness · Jul 5, 2026

  79. Batch delegation assigns each permission to an agent, then filters at token exchange

    Draft · · IETF Datatracker · Yuan Ni et al. · Jul 3, 2026

  80. One implementer found a transaction-token rule that let any scope through; the OAuth group fixed it in weeks

    Draft · · IETF Datatracker · Dhruv Agnihotri · Jun 23, 2026

  81. A June OAuth draft logs each hand-off between AI agents, but the per-hop limits the act claim lacks are optional

    Draft · · IETF Datatracker · Dapeng Liu et al. · Jun 8, 2026

  82. 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

  83. Atlassian's first draft for offline delegation banned bearer handles; revision 05 just recommends sender binding

    Draft · · IETF Datatracker · Larry Zhu et al. · May 22, 2026

  84. Three vendors put MCP controls in three different places in May, and only Auth0's was GA

    Release tracker · · 10 vendors' release notes · May 2026

  85. A 'decentralized' agent identity draft blocks risky calls when its Registry is down, and did:aip is taken

    Draft · · IETF Datatracker · Paras Singla · Apr 17, 2026

  86. An agent certificate draft ties access to a trust score set by the issuing CA, usually the agent operator's own

    Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Apr 10, 2026

  87. A proposed record of who authorized an AI agent's actions cannot yet prove which agent took them

    Paper · · arXiv · Asiri Dalugoda, Helixar · Apr 6, 2026

  88. 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

  89. OpenID agent-claims draft adds a provider-set user, application or agent label; scores stay each provider's own

    Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Mar 26, 2026

  90. AIP puts an agent's delegation chain in the token; its perfect score against attacks tests rules only AIP has

    Paper · · arXiv · Sunil Prakash · Mar 25, 2026

  91. A cross-domain agent trust draft requires the call chain, then leaves its format to a version that never came

    Draft · · IETF Datatracker · Daniel King et al. · Mar 15, 2026

  92. 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

  93. Google DeepMind wants agent authority to narrow at every hand-off, and misreads MCP's scopes on the way

    Paper · · arXiv · Nenad Tomašev et al. · Feb 12, 2026

  94. Auth0's AgentCore guide says prompts alone are not enough, then lets the prompt decide when to ask a person

    Article · · Auth0 Blog · Kapil Patil · Feb 10, 2026

  95. A Cisco-led agent draft puts the verifiable credential at a public URL, with selective disclosure a SHOULD it does not yet show

    Draft · · IETF Datatracker · Jean Diaconu et al. · Feb 6, 2026

  96. In February Okta let AI agents reach its management APIs over MCP; Cloudflare added controls on MCP connections

    Release tracker · · 7 vendors' release notes · Feb 2026

  97. Auth0's case for Token Vault: take the user ID out of the token call and let the session prove whose token it is

    Article · · Auth0 Blog · Abhishek Hingnikar, Okta · Nov 4, 2025

  98. AAGATE maps NIST's AI risk framework onto Kubernetes, and its paper never times the 'millisecond kill switch'

    Paper · · arXiv · Ken Huang et al. · Oct 29, 2025

  99. Huawei-led OAuth draft lets clients chain narrower tokens offline but leaves revocation delivery out of scope

    Draft · · IETF Datatracker · Li Ruochen et al. · Oct 20, 2025

  100. A refresh-token thief who waits for the app to close slips past reuse detection

    Article · · Auth0 Blog · Maria Vasilevskaya, Okta · Oct 8, 2025

  101. One author's OpenID Connect for Agents proposal checks each delegation hop but makes the chain optional

    Paper · · arXiv · Subramanya Nagabhushanaradhya · Sep 30, 2025

  102. Agentic JWT binds an agent's token to its task and its own code, but it is one author's draft, not a standard

    Paper · · arXiv (cs.CR preprint 2509.13597) · Abhishek Goswami · Sep 16, 2025

  103. A WSO2 draft puts the AI agent in OAuth consent and the access token, but not how the agent gets its credential

    Draft · · IETF Datatracker · Thilina Shashimal Senarath et al. · Aug 26, 2025

  104. 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

  105. An agent's plan fixed before it reads untrusted data still leaves each call's arguments open to injection

    Paper · · arXiv · Luca Beurer-Kellner et al. · Jun 10, 2025

  106. ETDI would sign MCP tool definitions against lookalikes, but leaves open who vouches for the publisher's key

    Paper · · arXiv · Manish Bhatt et al. · Jun 2, 2025

  107. A Cloud Security Alliance paper wants AI agents on a new identity stack, with OAuth kept for simple cases

    Paper · · arXiv (cs.CR preprint 2505.19301) / Cloud Security Alliance · Ken Huang et al. · May 25, 2025

  108. RFC 9068 makes resource servers check a JWT access token's type and audience, and warns a client could pose as a user

    Article · · RFC Editor · Vittorio Bertocci, Okta · Oct 1, 2021

  109. The token exchange RFC that agent designs cite says its record of earlier actors is not for access decisions

    Article · · IETF Datatracker · Michael B. Jones et al. · Jan 1, 2020

  110. RFC 8252 puts native-app OAuth authorization outside the host app’s browser control

    Article · · IETF / RFC Editor · William Denniss et al. · Oct 1, 2017

  111. RFC 7519 makes "none" mandatory to implement and leaves refusing an unwanted algorithm as a SHOULD

    Article · · RFC Editor · Michael B. Jones et al. · May 1, 2015

  112. RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023

    Article · · RFC Editor · D. Hardt et al. · Oct 2012

  113. A 2025 workload identity draft kept credential exchange for crossing trust domains, and never to gain more trust

    Draft · · IETF Datatracker · Arndt Schwenkschuster, Defakto · Mar 3, 2025

In our columns

  1. Gartner's identity curve needs a closer look at what has actually shipped

    Column · Oct 15, 2026

  2. The one settled agent rule is a buying test: reject products that sign in as the user

    Column · Oct 9, 2026

  3. Agent tokens leave out who acted, so keep the log where agents can't reach it

    Column · Oct 5, 2026

  4. Reused OAuth is winning the agent standards race and leaves sub-agent narrowing to vendors

    Column · Sep 30, 2026

  5. The one agent delegation chain we've seen running was built in-house; plan to build yours

    Column · Sep 22, 2026

Related terms

What appears alongside OAuth Token Exchange in the same briefings.

OAuth Identity and Authorization Chaining Across DomainsTransaction TokensIdentity Assertion Authorization GrantWIMSE ArchitectureCIBAAuth0 Agent GatewayZeroIDSD Agent (SD-Card)

Was this explainer useful?

Share this explainer

Pass it on. Every claim has a permanent number, so what you share today still points at the same words next year.