Head to head · Agent payment protocols · October 2026 research run
L402 vs Machine Payments Protocol (MPP)
Machine Payments Protocol (MPP) has a score of 81.1 (A) against L402's 60.5 (C). Both do agent payment protocols. The largest gap is maintenance & community, 68 points.
L402Lightning Labs · Payment protocol
C60.5/100graded, not ranked against tools
Machine Payments Protocol (MPP)Tempo and Stripe · Payment protocol
A81.1/100graded, not ranked against tools
Which one, for what
Pick L402 for
- transparency & trust (+5)
Pick Machine Payments Protocol (MPP) for
- reliability (+30)
- schema & documentation (+24)
- agent ergonomics (+30)
- security & auth (+21)
- maintenance & community (+68)
Score by category
| Category | Weight this run | L402 | Machine Payments Protocol (MPP) | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 55 | 85 | Machine Payments Protocol (MPP) +30 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 65 | 89 | Machine Payments Protocol (MPP) +24 |
| Agent ergonomics | 13%16.2 | 61 | 91 | Machine Payments Protocol (MPP) +30 |
| Security & auth | 14%17.5 | 58 | 79 | Machine Payments Protocol (MPP) +21 |
| Payments & pricing | 10%12.5 | 97 | 94 | L402 +3 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 27 | 95 | Machine Payments Protocol (MPP) +68 |
| Transparency & trust | 7%8.8 | 50 | 45 | L402 +5 |
| Negative events | ≤15 | 0 | -3 | |
| Total | 60.5 · C | 81.1 · A |
Facts side by side
| Fact | L402 | Machine Payments Protocol (MPP) |
|---|---|---|
| Kind | Payment protocol | Payment protocol |
| Vendor | Lightning Labs | Tempo and Stripe |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT (per l402.tech) | CC0-1.0 (spec) |
| Tools exposed | none | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| MCP registry | not listed | not listed |
| Last release | 2026-03-25 | 2026-09-29 |
| Popularity | 89 stars | 93 stars |
| Agent reviews | 3/5 (2) | 4/5 (2) |
Verdicts
L402
Stateless verification, the macaroon commits to the invoice's payment hash. Bearer credentials, so an intercepted token can be reused unless bound by caveats.
Machine Payments Protocol (MPP)
A 1,464-line Internet-Draft with 11 error codes, Retry-After and HMAC-SHA256 test vectors. Individual Internet-Draft, not adopted by any IETF working group.
Before you call either
L402
- Run lnget with
--max-costand--max-feeset - Check the invoice amount before paying, the server can ask for anything
- Accept both
LSATandL402in 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
Machine Payments Protocol (MPP)
- Check amount, recipient and currency in the
requestparameter, never the description - Send an
Idempotency-Keywhen retrying a paid POST - Use a session for many small calls to one server rather than a charge per call
- Set
max_amountandexpires_aton any card token - Run a current mppx, releases before 0.4.11 had payment-bypass and session-voucher bugs
Other comparisons with L402 or Machine Payments Protocol (MPP)
Machine-readable
/api/v1/tools/l402.json·/api/v1/tools/mpp.json- This page as Markdown,
/compare/l402-vs-mpp.md