L402 by Lightning Labs

# Fix list: L402

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/l402, the October 2026 research run, assessed 1 October 2026. Grade C, 60.5 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on L402: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 55 out of 100, up to 9 more on the total

Why it scored 55: Graded as a protocol on reference implementations (30), public servers (25), spec stability (25) and test suites (20). Lightning Labs ships Aperture (a Go reverse proxy), lnget (a Go client) and l402sdk (a Rust core with Python, Go and WASM bindings that has no tagged release yet), and the spec still points to third-party JavaScript libraries (22). There's no facilitator role and no directory, and the named production users are Lightning Labs' own Loop and Pool (8). A standalone RFC-style spec rewritten in March 2026 and unchanged since 20 March, while the bLIP-0026 pull request has been open since 7 June 2023 with the maintainers moving work to their own repository (15). No test vectors in the spec, but Aperture has unit tests for tampered tokens and l402sdk runs a regtest suite against Aperture with LND and Core Lightning (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Security & auth, 58 out of 100, up to 7.4 more on the total

Why it scored 58: The credential is a bearer macaroon plus preimage, and the spec says an intercepted one can be reused. Binding to an IP, TLS certificate or origin through caveats is optional (18). Caveats can narrow a token's expiry and scope before it's handed to another agent, lnget has --max-cost and --max-fee, and the spec says clients SHOULD enforce a maximum payment (15). Clients MUST check the invoice amount before paying, since a server can ask for any sum (10). Lightning payments leave a preimage as proof but no receipt header, and Aperture adds a dashboard and Prometheus metrics for operators (8). No SECURITY.md in Aperture, no published advisories, and open Aperture issue 272 (13 August 2026) reports that its MPP receipt header attests success without verifying the credential (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 3. Maintenance & community, 27 out of 100, up to 6.4 more on the total

Why it scored 27: The last tagged release is Aperture v0.5.0 on 25 March 2026, 190 days before the run date, though commits on its main branch continue to 1 October (0). No tagged releases in the last 90 days across the spec, Aperture, lnget or l402sdk (0). Aperture has 31 open issues, a batch of seven filed on 12 and 13 August still unlabelled, and the bLIP pull request has sat open for over three years (12). lnget's last release is v1.1.0 from 20 March 2026 and l402sdk's changelog is all Unreleased (7). CI runs in Aperture, lnget and l402sdk and dependencies were updated on 1 October (8).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 4. Agent ergonomics, 61 out of 100, up to 6.3 more on the total

Why it scored 61: A 402, a Lightning payment and a retry, after which the same token works for later calls until its caveats expire (21). Caveats can carry expiry, service tiers and capabilities, but there's one price per challenge and no negotiation of options (12). No error vocabulary, so a client sees 402 or 401 and nothing more specific (6). Paying twice is avoided by reusing the token, and replay limits come only from caveats and revocation (12). Released clients and servers are Go only, the multi-language SDK is unreleased and the JavaScript options are third-party (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Schema & documentation, 65 out of 100, up to 5.7 more on the total

Why it scored 65: A header grammar in section 5.3 and a 533-line macaroon spec that defines minting, verification and caveats byte by byte (18). No llms.txt found, but the repository has an agent spec that states the whole protocol in about 560 tokens (7). The 402-line spec uses RFC 2119 language and covers HTTP and gRPC flows (17). Fields and caveat formats are defined, with less detail on the invoice parameters (11). Examples of challenge and credential headers, and no error codes beyond the status codes (7). No version number on the spec and no changelog, only a backwards-compatibility section for the LSAT name (5).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 6. Transparency & trust, 50 out of 100, up to 4.4 more on the total

Made of editorial 44, provenance 55.

Why it scored 50: l402.tech says MIT and the tools carry MIT or Apache-2.0, but the spec repository has no `LICENSE` file (18). No privacy statement for the protocol, and Lightning payments reveal less than on-chain transfers by design (10). Backwards compatibility with the LSAT name is specified, with no deprecation policy (8). Lightning Labs maintains the spec alone with no governance body, and the bLIP process has stalled (8).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: lightning.engineering, registered 2016-11-22 (9 years) (11 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Payments & pricing, 97 out of 100, up to 0.4 more on the total

Why it scored 97: L402 is a machine payment protocol (40). No protocol fee, the payer pays Lightning routing fees and the price arrives in the invoice (20). Free to implement, with MIT tools (20). A funded Lightning wallet is all an agent needs, no account, though getting a node or custodial wallet usually takes a person, and Nostr Wallet Connect support in l402sdk is unreleased (17).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Whether Lightning Labs plans a release of l402sdk or Aperture after v0.5.0.
- Whether the bLIP-0026 pull request will be merged or closed.
- How many services outside Lightning Labs accept L402 today, which no directory records.
- Whether Aperture issue 272 (MPP receipt without verification) affects deployed proxies.
- unchecked: Lightning Labs' vulnerability disclosure route for Aperture and lnget.

## Weaknesses

- Bearer credentials, so an intercepted token can be reused unless bound by caveats
- No tagged release since 25 March 2026, and l402sdk has never been released
- No `LICENSE` file in the spec repository
- No error codes beyond 402 and 401
- Named production users are Lightning Labs' own Loop and Pool

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Run lnget with `--max-cost` and `--max-fee` set
- Check the invoice amount before paying, the server can ask for anything
- Accept both `LSAT` and `L402` in challenges, servers still send both
- Reuse a paid token for later calls until its caveats expire rather than paying again
- Keep macaroons and preimages out of logs, they're bearer credentials

## What the review panel asked for

- Release the SDK
- Publish typical routing-fee figures

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.