OAuth Said the Call Was Authorized. It Said Nothing About Which Workload Would Run It.
A paper submitted to arXiv on 2 September 2026, ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use, names a gap it calls the post-authorization execution trust gap: remote OAuth authorization can correctly establish that a client is allowed to call a remote MCP tool, and still say nothing about whether the provider side workload that ends up executing the call is the workload, in the state, the authorization was ever meant to trust. Moona Intelligence reads what the paper's own reachable description establishes, connects it to a Risk Registry weakness this corpus already tracks under independent evidence, and keeps separate what a controlled research prototype demonstrates from what a production remote attestation deployment would still have to prove.
Event analysed: . This analysis was published on 7 September 2026.
No, according to ACLE-MCP: Attested Capability Leases for Execution-Time Trust in Remote LLM Tool Use, submitted to arXiv as 2609.02690 on 2 September 2026 by Zhiyang Ding, Yang Luo, Guangpu Chen, Qingni Shen and Zhonghai Wu of Peking University, listed under the Cryptography and Security (cs.CR) subject class. arxiv.org and its html mirror were both blocked at this session's network egress proxy on every attempted route, so the manuscript's own text could not be fetched or read directly here; everything attributed to the paper's own argument below rests on repeated, independently phrased web search passes whose result snippets converge on identical or near identical wording across separate queries, the same manual review evidence level this corpus already applies to other sources blocked the same way, including its own CONTINUITY record. The paper's own named problem, converged on identically across passes, is the post-authorization execution trust gap: a remote MCP service can correctly authorize that a client or user may call a given tool, while an endpoint the relying party still trusts by that authorization has since had its execution shifted to a substituted workload, is being served from stale appraisal state, or is reachable only through an undeclared downstream component the original authorization never named. ACLE-MCP's own proposed architecture, by the same convergent evidence, couples delegated OAuth authorization with a workload appraisal step and a resource side execution admission step, rather than treating a valid token as sufficient on its own. For a protected call, a Verifier appraises evidence from the target workload and returns a freshness bounded attestation result, and the system issues a short lived, sender constrained capability lease binding the expected workload identity, the operation, object and parameter bounds, a side effect budget, declared downstream constraints, the freshness requirement, and a receipt obligation. A provider controlled Execution Gate validates and consumes that lease immediately before protected tool logic begins, rather than at connection time. The reported prototype is a Python implementation with separate Verifier, lease issuer, gate and tool services, integrating standard Keycloak and OIDC access token validation with a server built on the MCP Python SDK, plus an optional vTPM path that replaces simulated evidence signatures with nonce bound quote generation and verification while preserving the same appraisal result, lease issuance and gate interfaces. Reported controlled security experiments, an attack suite whose blocking rate is computed against 190 attacks expected to be denied, and a component ablation covering authorization only, connect time attestation only, a stateful policy variant and a capability only variant, each converge on the same finding: every narrower design leaves at least one post-authorization attack family open, while the complete design is reported to block every evaluated attack family and preserve all benign tasks, at a reported pooled p95 latency increase from 12.20 milliseconds to 15.34 milliseconds, 25.7 percent, over OAuth alone on normal allowed calls. This record found no independently confirmed public source code repository for ACLE-MCP distinct from the paper's own text, and convergent search states plainly that the Keycloak and MCP integration path does not yet include production remote attestation, DPoP bound issuance, or a complete hardware trust chain, limitations this record treats as the paper's own rather than softening in either direction.
An OAuth token answers one question well: is this caller allowed to ask a remote service to do this. ACLE-MCP's own named contribution is pointing at the question sitting immediately behind it, one a valid token does not answer at all: once that call is admitted, which provider side workload, in which state, actually carries it out.
What the post-authorization execution trust gap names
Repeated, independently phrased web search passes converge identically on the paper's own framing. Remote Model Context Protocol services let a large language model agent invoke tools hosted somewhere the agent does not control directly. OAuth authorization, delegated through the usual client credential and token exchange machinery, is what establishes that the calling client or user is allowed to reach a given tool at all. What that authorization does not establish, on the paper's own account, is a fact about the far side of the call: that the concrete workload serving the request, right now, is the workload the relying party actually meant to trust when it decided the call was safe to authorize. The paper names three concrete ways that gap opens in practice, each converged on across separate search passes: execution can shift to a substituted workload behind the same authorized endpoint, the workload can still be the right one but be running against appraisal evidence that is no longer fresh, and the call can traverse a downstream component the original authorization decision never named or considered. A caller holding a genuinely valid token, presenting a genuinely correct request, can still end up authorizing an action for an execution context nobody actually vetted for this specific call.
The invocation boundary and the capability lease
ACLE-MCP's own proposed architecture, by the same convergent search evidence, is built around checking that second fact explicitly rather than assuming it. For a protected call, the system defines an invocation boundary carrying the audience, the tool, the operation, the object, parameter constraints, the declared downstream set, a side effect budget, and a minimum workload assurance policy the call requires. A Verifier appraises evidence from the target workload against that policy and returns a freshness bounded attestation result, one that is explicitly not assumed to remain valid indefinitely once issued. The system then issues a short lived, sender constrained capability lease combining the OAuth derived context, the workload appraisal, sender identity or proof, the invocation bounds, a freshness window, applicable policy versions, and any receipt obligation. A provider controlled Execution Gate, sitting immediately before protected tool logic actually runs, validates and consumes that lease at that exact moment, rather than relying on a check performed once back when the client first connected. Convergent search states the lease can bind the issuer, subject, audience, sender key, workload identity, tool, operation, object, parameter bounds, execution state constraints, the downstream set, the side effect budget, an appraisal digest, the policy version, a receipt requirement, an expiry, and a unique identifier, an unusually explicit list for what a single short lived credential is made to carry, and this record repeats it as reported rather than independently confirming every field's own name against the manuscript's text.
What the prototype actually integrates, and what its evaluation reports
Convergent search describes a Python prototype built as separate Verifier, lease issuer, gate and tool services, with what this record's sources describe as a realistic integration path: standard Keycloak and OIDC access tokens are validated as the OAuth layer, and admitted requests are forwarded to a server built on the MCP Python SDK. An optional vTPM path is described as replacing simulated evidence signatures with nonce bound quote generation and verification, while preserving the same appraisal result, lease issuance and gate interfaces the rest of the system already uses, which this record reads as the paper's own explicit acknowledgement that its default evaluation path does not depend on real hardware backed attestation. Reported evaluation results, converged on identically across separate search passes, describe a controlled attack suite whose blocking rate is computed against 190 attacks expected to be denied, alongside a component ablation across four narrower designs: authorization only, connect time attestation only, a stateful policy variant, and a capability only variant. Each narrower design is reported to leave a distinct class of post-authorization attack open, while the complete design is reported to block every evaluated attack family and to preserve all evaluated benign tasks at full success. The reported cost of that coverage is a pooled p95 latency increase, on normal allowed calls, from 12.20 milliseconds to 15.34 milliseconds against OAuth alone, a 25.7 percent increase this record repeats as reported rather than as independently measured.
Where this reaches Moona's existing registry
This record does not read ACLE-MCP's own threat model as naming a new failure class this registry lacks. Approval not bound to the executed action, AEW-005 in Moona's own Risk Registry, already names the general shape an approval attaching to what was presented for review rather than to whatever actually executes in its place, evidenced across a growing, independently sourced set of known examples this registry already carries, from a mutated shell environment to a destination substituted after a redirect to a formal conformance suite naming the same collapse directly. ACLE-MCP's own central claim, that authorization established at connection time does not by itself remain valid once a different, substituted, or staler workload is the thing actually consuming it, is the same binding failure applied to a specific object: not a diff, a commit, or a destination URL, but the provider side execution workload itself and the state it is appraised in. Its own further constraints, that a lease is sender bound rather than freely reusable by whichever caller happens to present it, and that a first authorized hop does not, on its own, authorize an undeclared downstream component the invocation reaches next, are already the shape this registry's own claimed authorization accepted without verification, AEW-007, and reachability treated as authority, AEW-008, exist to name, both already connected to AEW-005 in this registry's own relatedAews. This record connects ACLE-MCP to AEW-005 as a further known example of the same weakness, rather than minting a dedicated workload attestation weakness of its own; the underlying property, that an authority grant conditioned on an execution workload or workload state must still have that condition hold when the authority is actually consumed, is general, and this registry already owns the general shape independently of this one paper existing.
What this record does not establish
This record does not claim to have read ACLE-MCP's own manuscript text directly. arxiv.org and its html mirror were both blocked at this session's network egress proxy on every attempted route, and every claim above attributed to the paper's own argument rests on repeated, independently phrased web search passes whose result snippets converge on consistent wording across separate queries, not on a direct read of the primary text. This record found no independently confirmed public source code repository for ACLE-MCP under any of its five named authors, distinct from this corpus's own directly fetched reference implementation for the CONTINUITY paper; a reader should not assume a runnable public artifact exists merely because this record describes a prototype convergent search reports the paper as having built. This record does not claim the reported attack suite, ablation, or latency figures were independently reproduced, that the prototype has been deployed against a production remote MCP service, that its Keycloak and MCP integration path includes production remote attestation, DPoP bound issuance, or a complete hardware trust chain, limitations convergent search states the paper itself acknowledges, or that any vendor or standard has adopted this architecture. Where the evidence available to this record does not establish a fact, this record states it as unknown rather than inferring it from the shape this weakness class already shows elsewhere in this registry.
Sources
This analysis interprets third-party reporting, research and announcements. Moona is not the original reporter of the underlying events.
Protocol evidence
This record does not assess these architectures. The connection runs through the Risk Registry requirement each one bears on, and these published authority architectures are what the evidence says about that requirement.
Protocol evidence related through AEW-005 Approval not bound to the executed action
- Supports requirement
Agent Flight Recorder
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner (independent research, arXiv preprint)
Requirement Cryptographic binding of the approval field to the approver's identity and the specific action is described as a production deployment property, not an unconditional schema guarantee
This weakness's own known examples are, across every one of them, a case where an approval attached to nothing verifiable or a later state change went unchecked against a prior decision. Agent Flight Recorder's own schema keeps a human approval field and an execution field as two independently checkable facts rather than one narrative line, which is a direct answer to the underlying need this weakness names: an approval must bind to a specific action, not merely occur near one. It supports that requirement rather than implementing an enforced version of it, because the reported cryptographic binding of the approver's identity to the specific action applies only in production deployments of the construction, not as an unconditional schema guarantee, and the mechanism records the approval/execution relationship for later forensic inspection rather than checking it before the action dispatches the way EMILIA's action hash rejection or Codex CLI's authorization freshness recheck do.
- Supports requirement
Agent Infrastructure Control Protocol (AICP)
Tihan-Nico Paxton, Apollo Deploy (individual submission to the IETF)
Requirement An accepted approval binds cryptographically or transactionally to one exact plan revision
This weakness's own corrective response pattern calls for binding an approval to the exact action object by hash or an equivalent identity, and rejecting execution when the action presented for review differs from the action about to run. AICP's own Section 9.4 requires an accepted approval to be cryptographically or transactionally bound to the Plan identifier, exact revision, approving principal, material changes and expiry, stating directly that approval of prose alone is insufficient and that a changed revision is not authorized by the old approval. The HTTP binding in Section 14.5 enforces the same binding mechanically, through a conditional request against the Plan's strong entity tag. Recorded as design evidence for the requirement this weakness already states, not as a claim that any provider has implemented this draft's text.
- Supports requirement
An Architecture for Auditing Agent Delegation and Interactions (audit-architecture)
Mirja Kuehlewind (Ericsson) and Henk Birkholz (Fraunhofer SIT), individual submission to the IETF
Requirement Authorization is modeled as an ordered sequence of transitions, not a single current value
This weakness's own response pattern calls for recomputing an approval's binding to the exact action at the enforcement point rather than trusting an earlier decision, including the temporal window that decision was made under. The draft's Action Record carries an authorization scope and expiry alongside the action it bears on, and its Authorization Transition Record class exists specifically so the state in force at a given point in a run can be reconstructed rather than assumed from whatever is currently known. Recorded as design evidence for the general response pattern; this record's own evidence separately connects to a targeted extension of Moona's canonical Authority Resolution engine closing the equivalent gap in Moona's own runtime reasoning, not a claim that this draft's own text was implemented anywhere.
- Supports requirement
ChainIT Authority Protocol and Agent Subject Profile for pre execution authority validation
ChainIT
Requirement A canonical transaction digest is described binding payer, payee, destination, amount, currency or asset and payment rail to approval and execution
A canonical transaction digest binding payer, payee, destination, amount, currency or asset and payment rail to both approval and execution is a direct, more specific response to an approval that attaches to nothing in particular. This is the corrective this weakness describes, named at the level of concrete payment fields rather than a generic hashed parameter set.
- Supports requirement
Codex CLI 0.151.0, restored permission profiles and authorization bound Guardian classifications
OpenAI
Requirement A cached low risk score is checked against the current authorization state before it is allowed to approve, and a mismatch defers to strict review rather than proceeding
Codex CLI's own fix rechecks a cached decision against current authorization state before it is allowed to approve anything, refusing to let a decision computed under one state keep approving after that state has moved. Claude Code's own current plugin marketplace documentation, read directly, describes an installed plugin auto-updating on a version, commit or content digest signal with no described mechanism to diff, flag or gate a change to the plugin's own hooks.json specifically, so whatever authority a user's earlier trust decision represented is not shown to be rechecked once a later update changes what that plugin's bundled hooks execute. Codex CLI's own mechanism is the corrective the reviewed documentation does not describe for this specific binding.
- Supports requirement
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Implementations MUST reject an approval request whose action hash does not match a locally recomputed hash of the presented Action Object
EMILIA's requirement that an approval be rejected unless the action hash matches a locally recomputed hash of the exact action object is the binding these cases lack, where an approved command's behaviour is decided by state the approval never inspected.
- Supports requirement
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Offline verification does not establish current revocation status, and the draft requires a relying party to apply current policy and current status inputs before any new reliance decision
UiPath Maestro's own default on Refresh schema before call setting keeps an MCP tool's technical interface current immediately before each call, but nothing in UiPath's own documented behavior establishes that the parameter authority a workflow's configuration granted against the original schema is re evaluated once a later schema changes underneath it. That gap, a technically current interface with no stated authority re evaluation behind it, is exactly the condition EMILIA's own requirement, that a relying party apply current status rather than historical acceptance before a new reliance decision, exists to close. UiPath's mechanism supports the need for that requirement rather than implementing it, the distinction this dataset already keeps between this property's two linked entries. A preprint posted to arXiv on 3 September 2026, 2609.03340, Fresh Memory, Stale Plans, restates the same distinction for a derived plan specifically: an executor that has read a superseding revision of a shared requirement into its own memory can still execute a plan derived from the earlier revision, since refreshing the executor's memory does nothing to a plan already computed from the state that memory has since moved past, so current state and current authorization for a pending action are two different facts. Read at the manual review evidence level, corroborated through convergent search rather than a direct read of the primary text, since arxiv.org and every mirror this record attempted were blocked at this session's network egress proxy; treated as further support for the requirement, not as an implementation of it.
- Supports requirement
N-AALP, Native Agentic Application Layer Protocol (draft-bubblefish-naalp)
BubbleFish, individual submission to the IETF
Requirement A signed-action-object model with a content-bound Approval and a single-use consume ledger is reported, not independently verified
This weakness's own response pattern calls for binding an approval to the exact action object, by hash or an equivalent identity, rather than to a name or a connection. The reported mechanism, an Approval bound under signature to the content id of the exact canonical argument object and, for an MCP call, a tool_id and args_id together, so a changed tool description or changed arguments yields a different approved call identity, would be a clean instance of exactly that pattern if it accurately reflects the draft's own filed text. This session could not independently verify that text through any reachable primary or secondary source, so this link is recorded conditionally: design evidence for the weakness's own already-established requirement, not confirmation that this specific draft implements it.
- Supports requirement
N-AALP, Native Agentic Application Layer Protocol (draft-bubblefish-naalp)
BubbleFish, individual submission to the IETF
Requirement A durable single-use consume ledger, and a stated limit that offline verification proves validity at issue, not current unspentness, are reported, not independently verified
This weakness's authorityGap states that authority attaches to what was presented for review, not automatically to whatever executes afterward; an approval a durable ledger has already recorded spent is not, in any meaningful sense, still attached to a further execution. The reported single-use consume ledger, and the reported statement that offline cryptographic verification proves validity at issue rather than current unspentness, would instantiate that gap precisely for a signed approval's own consumption state rather than its identity binding. Unverified by this session for the reason stated above; this record's own independent contribution is the additive extension it separately motivated to Moona's canonical Authority Resolution engine (an evidenced approval's singleUse/consumed state, consulted only when singleUse is evidenced true), which does not depend on this specific draft's own claims being confirmed.
- Supports requirement
The Missing Execution-Finality Protocol Layer of the Internet (draft-das-execution-finality-protocol-layer)
Sangram Das, individual submission to the IETF
Requirement A validated Candidate Act may produce a narrowly scoped, non-bearer Execution Handle bound to that one act and to the Finality Sink that will consume it
This weakness's own response pattern calls for binding an approval to the exact action object and recomputing that binding at the enforcement point rather than trusting possession of a credential. The non-bearer Execution Handle, corroborated through convergent search rather than a direct read of the filed text, generalizes exactly that principle to a credential class broader than one interface family: a validated Candidate Act may produce a handle scoped narrowly to that one act, and possessing the handle is not itself proof the currently presented act still matches the one it was issued for. Recorded as documented design evidence restating this weakness's own already-established requirement at a general level, not as independent confirmation that this specific umbrella draft's own mechanism is demonstrated running anywhere.
- Supports requirement
The Missing Execution-Finality Protocol Layer of the Internet (draft-das-execution-finality-protocol-layer)
Sangram Das, individual submission to the IETF
Requirement Formalizes Candidate Act, Non-Effective State, Protected Enforcement Domain, Execution Handle and Finality Sink as shared vocabulary for a family of domain-specific drafts
This weakness's own known examples had, before this addition, connected to draft-das-agentic-tool-binding-03 as though it were a freestanding architecture. Convergent search corroborates this draft as the umbrella that sibling instantiates: a Protected Enforcement Domain validates authority scoped to an act's purpose, destination, jurisdiction, freshness, revocation state, policy epoch, runtime integrity and effectuation-boundary identity together, a broader validation surface than the tool-binding draft's own two directly verified consequence classes. Recorded as design evidence for this weakness's own binding requirement at the general architecture level; this session located no reference implementation for this specific umbrella draft and does not treat any part of it as independently verified running code.
- Supports requirement
The Missing Execution-Finality Protocol Layer of the Internet (draft-das-execution-finality-protocol-layer)
Sangram Das, individual submission to the IETF
Requirement Fails closed on missing, stale, mismatched, replayed or unverifiable context
This weakness's own response pattern calls for rejecting execution when the action presented for review differs from the action about to run, rather than proceeding on a default allow. The signal that prompted this record carries a five-item fail-closed enumeration, missing, stale, mismatched, replayed or unverifiable context, consistent with the fail-closed behavior this weakness's own draft-das-agentic-tool-binding-03 known example already verified directly in running code for one narrower mechanism. This session's own independent search did not itself return that exact enumeration from a secondary source, so this link is recorded as documented design evidence consistent with corroborated evidence, not as independently re-confirmed word for word against the filed text.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement Authority is scoped to one Candidate Act through a deterministic digest of its own exact arguments
This weakness's own response pattern calls for binding an approval to the exact action object by hash or an equivalent identity and recomputing that binding at the enforcement point rather than trusting the request. Act Bound Authority, confirmed directly this session from the draft's own reference implementation, is exactly that binding applied to tool dispatch: a deterministic digest computed over a Candidate Act's own exact arguments, so authority issued for one call cannot be presented for a different call bearing different arguments even under the same session or workload. Recorded as design evidence independently demonstrated in running reference code, not as a claim that this specific implementation is deployed anywhere.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement A Finality Sink verifies authority atomically immediately before invoke() runs, fail closed on any failure
This weakness's own response pattern calls for recomputing an approval's binding at the enforcement point rather than trusting an earlier decision. The Finality Sink, confirmed directly this session from the reference implementation's own sink module, is that enforcement point positioned immediately before the underlying invoke() call, verifying authority atomically and blocking execution whenever verification does not succeed rather than proceeding on a default allow. Recorded as design evidence for the same requirement EMILIA's own action-hash rejection requirement already formalizes for payment operations, applied here to tool dispatch generally.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement Each parallel tool call requires its own independently computed authorization
None of this weakness's own known examples had, before this addition, named independent authorization for concurrent tool calls specifically. The reference implementation's own test scenarios, read directly this session, decide a parallel search plus unauthorized payout case as two independent authorization decisions rather than one session-level trust judgment covering an entire batch, closing a gap this weakness's own binding requirement implies but had not yet evidenced concretely for parallel dispatch.
- Supports requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement A retried or replayed call presenting already-consumed authority is denied
This weakness's own known examples document an approval or a cached decision surviving a state change it never accounted for; none had yet named a retried or replayed call presenting already-spent authority as its own distinct axis. The reference implementation's own replay store, read directly this session, marks authority consumed atomically on first use and denies a subsequent presentation of the same authority, with the implementation's own stated limitation that this protection is local rather than distributed. Recorded as design evidence for a property this weakness's own response patterns imply but had not yet evidenced at this level of precision.
- Implementation evidence
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Implementations MUST reject an approval request whose action hash does not match a locally recomputed hash of the presented Action Object
MoonPay's PayBox documents that any change to an operation's amount, merchant, destination, contract, function or secret name after submission forces a fresh approval request rather than letting the original one carry over. That is the same operation-bound approval EMILIA's action-hash rejection requirement formalizes cryptographically, arrived at independently in a live consumer product rather than a draft specification, which corroborates that the requirement is buildable outside a standards process.
- Implementation evidence
EP Authorization Receipts (EMILIA Protocol)
Iman Schrock, EMILIA Protocol, Inc., individual submission to the IETF
Requirement Offline verification does not establish current revocation status, and the draft requires a relying party to apply current policy and current status inputs before any new reliance decision
Codex CLI's own merged fix binds a cached Guardian v2 classification to the exact authorization state it was scored against and refuses to let it approve an action once that state has moved, arrived at independently in a shipped product rather than a draft specification. That corroborates EMILIA's own requirement that a relying party apply current status inputs before a new reliance decision rather than treat historical acceptance as still current, the same binding failure this weakness already describes. OpenMAIC's own 1.0.1 fix, read directly by this dataset, applies the identical principle to a network destination rather than a cached score: fetchWithRedirectValidation re-runs validateUrlForSSRF against every redirect hop before following it, rather than treating the single validation performed against the caller's originally supplied bring your own key base URL as still current once an ordinary HTTP redirect substitutes a different destination. A third independent, shipped instance of the same requirement, this one at a network authority boundary rather than at an approval or a classification.
- Missing requirement
ChainIT Authority Protocol and Agent Subject Profile for pre execution authority validation
ChainIT
Requirement No canonicalization algorithm, serialization format or independent test of the transaction digest against a live or reference transaction was found
Naming the fields a digest binds is not the same fact as a demonstrated binding. No canonicalization algorithm, serialization format or independent test of the digest against a live or reference transaction was found, so whether an executed transaction can be proven identical to the one approved remains a missing requirement rather than a closed one.
- Missing requirement
Codex CLI 0.151.0, restored permission profiles and authorization bound Guardian classifications
OpenAI
Codex CLI's own shipped Guardian v2 fix binds a cached tool call classification to the exact authorization state it was scored against, refusing to let a stale classification approve a call once that state has moved. GitHub issue 43549, read through this session's own automated web fetch and summarization tool, reports a materially different gap this record's own reviewed material states nothing about: whether a tool call's own reported terminal status, here the literal status aborted following the caller's own interruption, is checked against the account level effect that call already produced before reporting that status. The reviewed protocol record binds a decision to the state it was made under; it does not, on the material available to this session, bind a call's own reported outcome to the state the call actually left behind.
- Missing requirement
tool_use Is Not invoke(): Binding Execution Finality to Agentic Tool Call Interfaces and MCP (agentic-tool-binding)
Sangram Das, individual submission to the IETF
Requirement The reference implementation ships under a restricted evaluation license, not open source
Demonstrating a binding mechanism in reference code is not the same fact as that mechanism being available for production adoption. This session's own direct read of the reference implementation's LICENSE.md confirms a source-available evaluation license, not open source, explicitly denying production deployment and commercial use and reserving patent rights outside evaluation. Recorded as a missing requirement for anyone evaluating this reference implementation as a buildable corrective rather than as design evidence, not as a claim against the underlying architecture the draft itself describes.