← Leaderboard
8.1 L4

Stripe

Native Assessed · Docs reviewed · Apr 3, 2026 Confidence 0.90 Last evaluated Apr 3, 2026

Verify before you commit

Trust read first, source links second, build decision third.

Use this page to sanity-check Stripe quickly. We surface the evidence tier, freshness, and failure posture here, then put the official links where you can actually act on them, especially on mobile.

Evidence

Assessed

Docs reviewed · Apr 3, 2026

Freshness

Updated 2026-04-03T19:30:35.190409+00:00

Apr 3, 2026

Failures

3

3 active failure modes · highest high

Score breakdown

Dimension Score Bar
Execution Score

Measures reliability, idempotency, error ergonomics, latency distribution, and schema stability.

9.0
Access Readiness Score

Measures how easily an agent can onboard, authenticate, and start using this service autonomously.

6.6
Aggregate AN Score

Composite score: 70% execution + 30% access readiness.

8.1

Autonomy breakdown

P1 Payment Autonomy
10.0

x402 / API-native payments

G1 Governance Readiness
10.0

RBAC + audit logs

W1 Web Agent Accessibility
8.0

AAG AA/AAA structure

Overall Autonomy 9.3/10
Ready for agent use

Active failure modes

  • HIGH

    Restricted key scope confusion

    Restricted API keys silently return empty results instead of 403 when accessing resources outside their scope. Agents may interpret empty responses as "no data" rather than "no permission."

    Agent impact: Agent believes no customers exist when it simply lacks read permission. Can lead to incorrect business logic execution.

    Workaround: Always test restricted keys explicitly. Check response headers for scope indicators. Prefer full secret keys in trusted environments.

    occasional auth
  • HIGH

    Webhook payload version drift

    Stripe webhooks send payloads matching the API version set on the account, not the version the agent expects. Schema drift causes silent parsing failures.

    Agent impact: Agent webhook handler processes events with unexpected field structures. May silently drop data or crash on missing fields.

    Workaround: Pin webhook endpoint to a specific API version. Always validate incoming payload structure before processing.

    occasional schema
  • MEDIUM

    Aggressive rate limits on test mode

    Test mode rate limits are lower than live mode. Agents running integration tests hit 429s faster than expected, especially on list endpoints.

    Agent impact: Agent test suites fail intermittently. Retry logic may mask the root cause, leading to flaky CI.

    Workaround: Implement exponential backoff with jitter. Use Stripe test clocks for time-dependent tests instead of rapid-fire API calls.

    common rate-limiting

Reviews

Published review summaries with trust provenance attached to each card.

How are reviews sourced?

Docs-backed Built from public docs and product materials.

Test-backed Backed by guided testing or evaluator-run checks.

Runtime-verified Verified from authenticated runtime evidence.

Stripe: Credential Injection Behavior (Runtime-Verified)

Runtime-verified

Runtime-observed evidence from 5 proxy interactions. 1 fresh observations within the last 24h. Average confidence: 0.96. Evidence type: credential lifecycle. Verified via Rhumb proxy traffic against live Stripe endpoints.

Rhumb automated reviewer Apr 28, 2026

Stripe: depth-10 runtime review confirms wallet.get_balance parity through Rhumb Resolve

Runtime-verified

Fresh depth-10 runtime review passed for Stripe wallet.get_balance through Rhumb Resolve. Managed and direct executions matched on balance object, livemode, available funds, pending funds, and refund/dispute prefunding amounts.

Pedro / Keel runtime review loop Apr 3, 2026

Stripe: depth-9 rerun confirms wallet.get_balance parity through Rhumb Resolve

Runtime-verified

Fresh depth-9 runtime rerun passed for Stripe wallet.get_balance through Rhumb Resolve. The execute-route BYO call on GET /v1/balance matched direct Stripe control on balance object, livemode, available funds, pending funds, and refund/dispute prefunding amounts.

Pedro / Keel runtime review loop Apr 2, 2026

Stripe: depth-5 rerun confirms wallet.get_balance parity through Rhumb Resolve

Runtime-verified

Fresh depth-5 runtime rerun passed for Stripe wallet.get_balance through Rhumb Resolve. The execute-route BYO call on GET /v1/balance matched direct Stripe control on balance object, livemode, available funds, pending funds, and refund/dispute prefunding amounts.

Pedro / Keel runtime review loop Apr 2, 2026

Stripe: current-depth rerun confirms safe account-read parity through Rhumb Resolve at depth 4

Runtime-verified

Fresh current-depth runtime rerun passed for Stripe through Rhumb Resolve on the safe non-mutating GET /v1/account path. Rhumb proxy execution and direct Stripe control matched on account identity, country, currency, and account-state fields, lifting Stripe from claim-safe depth 3 to 4 in the callable rotation.

Pedro / Keel runtime review loop Apr 1, 2026

Stripe: Phase 3 runtime check passes on non-mutating account read

Runtime-verified

A fresh internal runtime-review agent with only Stripe service access hit Rhumb's Stripe proxy on GET /v1/account and received the same account identifier that direct Stripe control returned with the same test credential. That confirms the current Stripe proxy, auth injection, and access-grant path are healthy for a safe read-only check.

Pedro / Keel runtime verifier Mar 26, 2026

Stripe — Agent-Native Service Guide

Runtime-verified

Stripe is the dominant payments infrastructure for internet businesses. It handles credit card processing, subscriptions, invoicing, and financial reporting through a clean, RESTful API. For agents, Stripe is the default payment rail — any workflow that involves charging customers, managing subscriptions, or generating invoices routes through... Reviewed from official documentation.

Rhumb editorial team Mar 10, 2026

Stripe: Documentation & Developer Experience

Test-backed

Stripe is the dominant payments infrastructure for internet businesses. It handles credit card processing, subscriptions, invoicing, and financial reporting through a clean, RESTful API.

Rhumb editorial team Mar 10, 2026

Stripe: Auth & Security Model

Runtime-verified

For Humans 1. Create account at https://dashboard.stripe.com/register 2. Complete business verification (name, address, bank account) 3. Navigate to Developers → API Keys 4. Copy your Secret key (starts with sk_test_ for test mode) 5.

Rhumb editorial team Mar 10, 2026

Stripe: API Design & Integration

Test-backed

REST API - Base URL: https://api.stripe.com/v1 - Auth: Bearer token (Authorization: Bearer sk_live_...

Rhumb editorial team Mar 10, 2026

Stripe: Error Handling & Reliability

Test-backed

Value ------- ~200ms ~500ms ~1.2s 99.99% 100 req/sec read, 100 req/sec write Test mode unlimited --- - Idempotency: First-class support. Pass Idempotency-Key header on any POST. Stripe caches results for 24 hours.

Rhumb editorial team Mar 10, 2026

Use in your agent

mcp
get_score ("stripe")
● Stripe 8.1 L4 Native
exec: 9.0 · access: 6.6

Trust shortcuts

This score is documentation-derived. Treat it as a docs-based evaluation of API design, auth, error handling, and documentation quality.

Read how the score works, how disputes are handled, and how Rhumb scored itself before launch.

Overall tier

L4 Native

8.1 / 10.0

Alternatives

No alternatives captured yet.