Verifiable Intent
Mastercard verifiable intent · agent-intent/verifiable-intent · VI
A specification for recording, in a chain of signed credentials, what a person authorised an AI agent to buy, so a merchant or payment network can check a purchase against that record.
In our briefings
The claim each of the newest briefings on Verifiable Intent would have you leave with.
Verifiable Intent chains three layers of signed SD-JWT credentials, tokens whose fields can be shown selectively. The issuer, a bank or payment network, binds the user's key for about a year (L1). The user signs mandates for the agent (L2): final values for an immediate purchase or, in autonomous mode, constraints plus the agent's key for a recommended 24 hours to 30 days. In autonomous mode the agent then signs a payment mandate for the network and a checkout mandate for the merchant, each valid about five minutes (L3a, L3b). The specification says "Layer 3 credentials MUST NOT contain a `cnf` claim in the payload (terminal delegation)", so the agent's credential names no next key and the agent cannot pass its authority to another agent. A verifier checks the agent's final values against the user's constraints, but only the ones disclosed to it, and it skips the allowlist check when no allowlist was disclosed. Eight constraint types are defined (merchants, line items, payees, amount range, budget, recurrence, agent recurrence, reference). Budget and the two recurrence limits need the payment network to keep a running count.
Verifiable Intent stops an AI agent from passing its buying authority on, and v0.1 has no protocol to revoke itBI-FIND-2026-0477
Token Status List puts the status of many tokens in a signed, compressed bit array per list, which the authors size for up to millions of tokens, and an issuer may run several lists. Each token carries an index and the list's URI. A verifier fetches the list, validates it and reads the token's 1, 2, 4 or 8 bits for VALID, INVALID, SUSPENDED or an application-specific value. Because many tokens share one list, the issuer does not learn which token a verifier is asking about, which the authors call herd privacy. With OAuth introspection, by contrast, the verifier contacts the issuer about each token. The draft warns that an issuer could defeat this with a unique list or list URI per token, which relying parties that verify many tokens can spot by comparing the number and size of lists with the tokens they see. The uri and index pair is unique to each token, so the draft also warns that a relying party may track one token's status over time and that colluding parties may link two transactions involving the same token; it recommends batches of one-time-use tokens. A revocation reaches a verifier when it next fetches the list, and the issuer can signal how long a copy may be cached through the list's exp and ttl.
OAuth's token revocation list nears RFC, and a shared list hides which token is checkedBI-FIND-2026-0632
Section 6 of EMVCo's framework presents Verifiable Intent v0.1 as one realisation of its three layers and sends reviewers to "the authoritative repository maintained by FIDO" for the current text, which it says continues to evolve. Verifiable Intent is a chain of SD-JWT verifiable credentials. A payment credential provider signs the first, and the named candidate is EMVCo's own Card Digital Payment Credential (DPC). The consumer signs the second through a wallet. In autonomous mode that layer carries the agent's key, and the agent signs a third layer of two credentials, a closed Payment Mandate and a closed checkout mandate, each bound by hash to Layer 2 and both tied to the hash of a merchant-signed checkout; in immediate mode the chain stops at the consumer's layer. Selective disclosure keeps the two apart: the merchant receives the checkout mandate, the payment system the Payment Mandate, and neither can reconstruct disclosures it was not given. A verifier in permissive mode may skip a constraint type it does not recognise, though the framework says security-critical verifiers should treat one as a failure. Section 1.2.2 declares credential-format primitives such as SD-JWT structures out of scope, and section 6.7 then specifies SD-JWT VC as Verifiable Intent's format. We read the consumer and agent layers as the open and closed mandates of Google's AP2, which the framework's text does not name.
EMVCo's agent card-payment draft binds no one yet and points to a spec FIDO maintains for proof of consentBI-FIND-2026-0440
›Cited in 19 briefings
Every briefing that discusses this term, newest first.
- Verifiable Intent stops an AI agent from passing its buying authority on, and v0.1 has no protocol to revoke it
Article · · Verifiable Intent (GitHub, agent-intent/verifiable-intent) · Verifiable Intent Working Group · Apr 18, 2026
- OAuth's token revocation list nears RFC, and a shared list hides which token is checked
Draft · · IETF Datatracker · Tobias Looker et al. · Aug 13, 2026
- 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
- FIDO's marketing chief calls agent identity 'not a thing' and asks the industry to hang on for a standard
Podcast · · Authentic Talks - An HID Podcast · What FIDO Alliance Sees Next: Passkeys, AI Agents, and the Future of Identity? · Jun 23, 2026
- Google's AP2 v0.2 ties an agent's purchase to the merchant's own signed checkout by hash
Article · · ap2-protocol.org · Google · Apr 28, 2026
- 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
- The SD-JWT standard that agent drafts build on never mentions agents and leaves key binding to each verifier
Article · · IETF (RFC Editor) · Daniel Fett et al. · Nov 20, 2025
- A draft records every AI agent verdict, refusals too, and won't let a dispatched action pass as confirmed
Draft · · IETF Datatracker · Steven Mih, Action State Group · Sep 27, 2026
- Schrock's receipts prove a named key approved one exact agent action, and the draft lists at length what they cannot prove
Draft · · IETF Datatracker · Iman Schrock, EMILIA Protocol · Sep 12, 2026
- OpenID experts tell EMVCo an agent's payment can look like the cardholder's, and no one vouches for the agent
Article · · OpenID Foundation · Serj Hallam et al. · Oct 8, 2026
- 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
- Visa, Mastercard and Ant have begun talks on 'Know Your Agent', not agreed a standard
Article · · Forkast · Sep 10, 2026
- FIDO's agent authentication group is led by Google, OpenAI and a pharmacy chain; card networks lead payments
Article · · FIDO Alliance · FIDO Alliance · Apr 28, 2026
- Agent payment protocols prove an agent may pay; a Toronto paper adds a step to check the job was done
Paper · · arXiv · Adrian de Valois-Franklin et al. · Jun 7, 2026
- 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
- 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
- Mastercard's Agent Pay began in April 2025 as a promise that payment agents would be registered and verified
Article · · Mastercard · Mastercard · Apr 29, 2025
- ATFAA names identity inheritance as an agent threat and answers it with existing cloud policy tools
Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 28, 2025
- An A2A threat model flags the Agent Card as an attack path, and its example flow never passes on the user's identity
Paper · · arXiv · Idan Habler et al. · Apr 23, 2025
Related terms
What appears alongside Verifiable Intent in the same briefings.
MastercardTrusted Agent ProtocolMandate (AP2)Agentic Commerce ProtocolAP2EMV Secure Remote CommerceKey Binding JWTFIDO Alliance