[OAUTH-WG] Re: [WIMSE] Re: Binding OAuth-authorized calls to specific tool-call arguments in agentic/MCP flows

Mohamad Khalil Yossif <mohamad@yuthent.com> Wed, 02 September 2026 09:32 UTC

Return-Path: <mohamad@yuthent.com>
X-Original-To: oauth@mail2.ietf.org
Delivered-To: oauth@mail2.ietf.org
Received: from localhost (localhost [127.0.0.1]) by mail2.ietf.org (Postfix) with ESMTP id 889D2133B3939 for <oauth@mail2.ietf.org>; Wed, 2 Sep 2026 02:32:25 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=ietf.org; s=ietf1; t=1788341545; bh=iSaBdmNIc3cm9XDgrNuEDokiYv4gbNvN+LmoiRHLRwk=; h=From:Subject:Date:Cc:To; b=jrXoaNpREXZvR9AwB2spjMwrJoo9xb1p+IIibsOzRBfyIjmQmOl3OfCMeeve19F9U /emPUrath4eeJLtBh/IdhvVD+tncu8yxlzyxJOB4t/7K22TSMJGNy72PBHQxiP3YyZ s6GPipVqlZCwOo42CuAGpkKFG2HcUpH0FLkCCIak=
X-Virus-Scanned: amavisd-new at ietf.org
X-Spam-Flag: NO
X-Spam-Score: 1.338
X-Spam-Level: *
X-Spam-Status: No, score=1.338 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HTML_MESSAGE=0.001, RCVD_IN_SBL_CSS=3.335, RCVD_IN_VALIDITY_RPBL_BLOCKED=0.001, RCVD_IN_VALIDITY_SAFE_BLOCKED=0.001] autolearn=no autolearn_force=no
Authentication-Results: mail2.ietf.org (amavisd-new); dkim=pass (2048-bit key) header.d=yuthent.com
Received: from mail2.ietf.org ([166.84.6.31]) by localhost (mail2.ietf.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id A9Ap7h0NjYPI for <oauth@mail2.ietf.org>; Wed, 2 Sep 2026 02:32:24 -0700 (PDT)
Received: from out-zbxj-a91.jellyfish.systems (out-zbxj-a91.jellyfish.systems [198.54.127.91]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-256) server-digest SHA256) (No client certificate requested) by mail2.ietf.org (Postfix) with ESMTPS id ACA63133B391A for <oauth@ietf.org>; Wed, 2 Sep 2026 02:32:24 -0700 (PDT)
Received: from mail.privateemail.com (unknown [79.177.159.87]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mail.privateemail.com (Postfix) with ESMTPSA id 4hZcvN1rk9zyNT; Wed, 02 Sep 2026 09:32:16 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yuthent.com; s=default; t=1788341537; bh=mOCpzaOPe3a2TWhHosEGSa6VBKRJTkXrD5EuTfw3SpY=; h=From:Subject:Date:Cc:To:From; b=XNvcN5v3or2F2rn2Wmzjier44uF7dB9pMpFfEKRzDknzZl31HmRqQTKTOALr6Wnv7 USSaPN3ch2StzH+cC1dtx4PEdSxP0JfAuJog03cO9QGtLGIdsYFkJQf60aWeIJxJ2I v0Y59d8o0gRr44gshB8Oevh/UgQEUudRUS8FDjeySU/6nXGfCKAJdTr3zUJNsYnBmg IzrP9Ty0lvMJ/WFyAHTaZTNZ+aK/q5bx+rmeaNR7BEvT2dmsBkJA5KoojNQ5/ZJrMt vi2dvyVncIWIdPkK1ZP/5/K7xoFimhkX2cxa7FJupqKIOC7oquq92Ie6YgppTu/8B+ YgyKithLyUW1w==
From: Mohamad Khalil Yossif <mohamad@yuthent.com>
Content-Type: multipart/alternative; boundary="Apple-Mail=_E757C288-62D6-47C2-9629-2ABAEA13AA23"
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3864.700.51.1.1\))
Message-Id: <9D4E9285-A6D4-4A12-8455-ADAEA9252043@yuthent.com>
Date: Wed, 02 Sep 2026 12:32:04 +0300
To: oauth@ietf.org
X-Mailer: Apple Mail (2.3864.700.51.1.1)
X-Envelope-From: mohamad@yuthent.com
Message-ID-Hash: R7OZJDAHUMK6JHVHL7NXQPPNFHHMNWPU
X-Message-ID-Hash: R7OZJDAHUMK6JHVHL7NXQPPNFHHMNWPU
X-MailFrom: mohamad@yuthent.com
X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; header-match-oauth.ietf.org-0; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header
CC: Yaron ZEHAVI <yaron.zehavi@rbinternational.com>, info@sangamdas.com
X-Mailman-Version: 3.3.9rc6
Precedence: list
Subject: [OAUTH-WG] Re: [WIMSE] Re: Binding OAuth-authorized calls to specific tool-call arguments in agentic/MCP flows
List-Id: OAUTH WG <oauth.ietf.org>
Archived-At: <https://mailarchive.ietf.org/arch/msg/oauth/CDImCNp7XqLe76EF38fCwh11KqA>
List-Archive: <https://mailarchive.ietf.org/arch/browse/oauth>
List-Help: <mailto:oauth-request@ietf.org?subject=help>
List-Owner: <mailto:oauth-owner@ietf.org>
List-Post: <mailto:oauth@ietf.org>
List-Subscribe: <mailto:oauth-join@ietf.org>
List-Unsubscribe: <mailto:oauth-leave@ietf.org>

> Yaron, Sangam,
> 
> Yaron asked what gap fine-grained authority properties cannot mitigate.
> I think there is one, and the RAR example is the clearest way to show
> it.
> 
> Take the authorization detail as written:
> 
>   "type": "payment_initiation",
>   "instructedAmount": { "currency": "EUR", "amount": "123.50" },
>   "creditorAccount": { "iban": "DE02100100109307118603" }
> 
> A resource server can deny anything that does not match. That is
> correct and it is the right mechanism for the job.
> 
> What it establishes is that this call is within what was authorized.
> What it does not establish is that a person approved this call.
> 
> Those are different facts and the distinction is not academic. Grant
> this detail once, and the agent may present it against an endpoint an
> hour later, a day later, or three hundred times, and every one of
> those calls matches. The parameters were approved as a shape. Whether
> a human was present for any particular execution, and approved that
> particular one, is not carried anywhere in the exchange.
> 
> Make the detail narrower and the gap does not close, it only shrinks:
> a single-use authorization detail bound to one amount and one IBAN
> still says the user consented to a payment of that shape, not that
> they consented at the moment the payment went out.
> 
> Which is fine for most flows. It stops being fine where the action is
> consequential and irreversible, and where someone has to reconstruct
> afterwards who authorized what. A regulator, a card issuer in a
> dispute, a counterparty. They arrive after the fact, they trust
> neither the client nor the authorization server, and there is no
> artifact for them to check. The grant tells them the agent was
> permitted. It does not tell them a human approved.
> 
> Yaron, your mission-bound point addresses a different half of this and
> I agree with it. An approved intent gives the enforcement gate
> something to evaluate against, and it does reduce how often the user
> must be asked. But the gate is still deciding on the strength of what
> the AS and the RS agreed, and neither of them is the human. Lowering
> consent friction and producing evidence of consent are separable
> goals, and a design can do the first well and leave the second
> untouched.
> 
> I wrote the requirements up without proposing a mechanism, because I
> do not think the mechanism belongs in a problem statement:
> 
>   https://datatracker.ietf.org/doc/draft-yossif-agent-mandate-problem/
> 
> It is cited in draft-chen-oauth-agent-authz-use-cases, where Section 5
> asks the same question in the use-case framing.
> 
> Two things I would genuinely like an answer to rather than agreement.
> 
> Is there a construction where a fine-grained authorization detail does
> establish that a human approved a specific execution, rather than
> approved a class the execution falls into? I have not found one, and I
> would rather be shown wrong than keep asserting a gap.
> 
> And where a regulator has to reconstruct the decision after the fact,
> what does a bank present today? That is a practitioner question and I
> am asking it as one.
> 
> Mohamad Khalil Yossif
> 
>   draft-yossif-agent-mandate-problem
>   https://datatracker.ietf.org/doc/draft-yossif-agent-mandate-problem/
>   draft-yossif-psea
>   https://datatracker.ietf.org/doc/draft-yossif-psea/