Stripe Agent Toolkit MCP Server

mcp.stripe.com · Agent-Commerce Infrastructure modeIntegrated

Last probed 2026-10-07 04:17 UTC · Provisional

Stripe Agent Toolkit MCP Server — Official remote MCP server exposing Stripe payments/billing tools to agents.

75 / 100triageInterrupt Score(range 44–94 · 9 properties unassessed)How much automated use this service interrupts — the badge-driving metric. Unassessed properties are provisionally scored at 50%; evidence-graded successes at 25%.

Custody / RiskUnknown

ConfidenceProvisional

Verdict: Partially — an AI agent can use Stripe Agent Toolkit MCP Server, but activate is blocked — Signup page loads a CAPTCHA widget — automated signup may be blocked (unverified).

DiscoverIncomplete
ActivateBlocked
OperateIncompletegated by Activate
ManageNot yet probedgated by Activate

Capability parity

Each stage answers one question about what an agent can do unattended. Stages are ordered by the credential-gateway dependency: Activate issues the keys that unlock Operate and Manage. A row marked “Not yet probed” means no probe has tried that capability yet — a different ledger from the “unassessed” properties under Findings, where no probe tier capable of catching that interrupt has run.

Discover

Can an agent find and read it, no account?

Incomplete

Assessment incomplete - not yet probed: Read pricing & limits without login.

Be found by a retrieval agentEasy
Retrieval access present.
Evidence
Path tried
robots.txt / sitemap / discovery headers
Where it stalled
completed
Evidence tier
Tier 1 (unauth probe)
Verification
Evidence-only — graded from passive signal, not live-verified.
Backing checks
retrieval_bot_access, sitemap_xml, link_header_discovery
Read what it does and how to use itEasy
Machine-readable docs present.
Evidence
Path tried
llms.txt / AGENTS.md / schema.org / docs
Where it stalled
completed
Evidence tier
Tier 1 (unauth probe)
Verification
Evidence-only — graded from passive signal, not live-verified.
Backing checks
llms_txt, markdown_content, content_signals
Read pricing & limits without loginNot yet probed
Public pricing was not confirmed - the page was absent, gated, or unreadable.

Activate

Can an agent sign up and walk away with the keys it needs?

Blocked

Assessment incomplete - not yet probed: Obtain an API / MCP access credential; Obtain a management / admin key.

Create an account self-serveBlocked
Signup page loads a CAPTCHA widget — automated signup may be blocked (unverified).
CAPTCHA / bot-challenge blocks this.
Evidence
Path tried
signup flow
Where it stalled
verification step
Evidence tier
Tier 1 (unauth probe)
Verification
Evidence-only — graded from passive signal, not live-verified.
- CAPTCHA / bot-challengeSignupSignup page loads a recaptcha CAPTCHA widget (matched: iframe[src*="recaptcha"]); widget presence does not prove automation is challenged — unverified.
Obtain an API / MCP access credentialNot yet probed
No self-serve credential signal detected - key issuance not yet probed.
Obtain a management / admin keyNot yet probed
No scoped or administrative key path was confirmed after activation.
Accept the terms without a bot-banEasy
No bot-prohibition signal found.
Evidence
Path tried
ToS / policy scan
Where it stalled
completed
Evidence tier
Tier 0 (passive scan)
Verification
Evidence-only — graded from passive signal, not live-verified.

Operate

Can an agent do the service's actual jobs — call, transact, pay?

Incomplete

Assessment incomplete - not yet probed: Pay via an agent rail (x402 / ACP / AP2).

Gated by Activate — the credential this stage needs isn't issued unattended, so these rows may be unreachable even where they read Easy.

Call the primary service over MCP / APIEasy
Machine interface present — evidence-only, not live-verified.
Gated by Activate — the credential this needs isn't issued unattended.
Evidence
Path tried
API / MCP / browser
Where it stalled
completed
Evidence tier
Tier 1 (unauth probe)
Verification
Evidence-only — graded from passive signal, not live-verified.
Backing checks
webmcp
Complete a transaction / checkoutNot applicable
Integrated tool — the API call is the transaction, no separate checkout.
Gated by Activate — the credential this needs isn't issued unattended.
Pay via an agent rail (x402 / ACP / AP2)Not yet probed
No agent-payment metadata detected - payment rails not yet probed.
Gated by Activate — the credential this needs isn't issued unattended.

Manage

Can an agent administer the account and provision resources?

Not yet probed

No probe has attempted this stage yet: Provision / scale / tear down a service; Change account details / set budget / rotate keys; View usage & billing; Cancel / export / delete (offboard).

Gated by Activate — the credential this stage needs isn't issued unattended, so these rows may be unreachable even where they read Easy.

Provision / scale / tear down a serviceNot yet probed
Not probed - provisioning is not part of the probe suite yet.
Gated by Activate — the credential this needs isn't issued unattended.
Change account details / set budget / rotate keysNot yet probed
Not probed - account admin is not part of the probe suite yet.
Gated by Activate — the credential this needs isn't issued unattended.
View usage & billingNot yet probed
Authenticated usage and billing access was not confirmed.
Gated by Activate — the credential this needs isn't issued unattended.
Cancel / export / delete (offboard)Not yet probed
No self-serve cancellation, export, or deletion path was confirmed.
Gated by Activate — the credential this needs isn't issued unattended.

Findings

How scoring works →

Interrupt tier: Moderate-Interrupt — derived from 1 finding; interrupt score 75 / 100 — the badge-driving metric. (range 44–94 · 9 unassessed)

Every tool starts at 100. Each interrupt found subtracts a penalty of base weight × timing × hardness × evidence — the multiplier values below come from the same rubric tables the score is computed with. New snapshots also provisionally subtract 50% of the full worst-case tax for each unassessed property and 25% for evidence-graded successes not live-verified by Tier 2.

Property coverage

A check only counts as clean when a probe tier capable of detecting that interrupt actually ran and found nothing. Not tested ≠ clean.

Property	Stage	State	Evidence	Required
CAPTCHA / bot-challenge	activate	failed	Active finding — itemized in the penalty matrix below. Tier 0 assesses this property.	no
SSO-only signup, no API-key issuance	activate	partial	Some coverage exists, but the available evidence is incomplete. Tier 1 assesses this property.	no
Mandatory phone verification call	activate	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
Mailed physical code (postal)	activate	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
“Contact sales” wall (no self-serve path)	activate	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
Manual approval queue	activate	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
ToS clause banning automated/bot access	discover	unassessed	Tier 0 (passive scan) ran but did not gather enough evidence to claim clean. Tier 0 assesses this property.	no
Rate-limit-triggered manual review	manage	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
One-time account / payment-method provisioning	manage	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
Identity / KYC verification	activate	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
Crypto wallet / key-custody setup	operate	unassessed	No probe tier that can detect this has run yet — unknown, not clean. Tier 2 assesses this property.	no
Email OTP verification	activate	success	None found — checked at Tier 1 (unauth probe) (evidence-graded; not yet live-verified by a Tier 2 probe) Tier 1 assesses this property.	no
SMS / phone OTP verification	activate	success	None found — checked at Tier 1 (unauth probe) (evidence-graded; not yet live-verified by a Tier 2 probe) Tier 1 assesses this property.	no
Mandatory redirect to vendor’s own site	operate	success	None found — checked at Tier 1 (unauth probe) (evidence-graded; not yet live-verified by a Tier 2 probe) Tier 1 assesses this property.	no
No Machine Interface	operate	success	None found — checked at Tier 1 (unauth probe) (evidence-graded; not yet live-verified by a Tier 2 probe) Tier 1 assesses this property.	yes

Interrupt found	Base weight	× Timing	× Hardness	× Evidence	= Penalty
Starting score					100
CAPTCHA / bot-challengeSignupSignup page loads a recaptcha CAPTCHA widget (matched: iframe[src*="recaptcha"]); widget presence does not prove automation is challenged — unverified.	6	×1one-time setup	×2.5hard	×0.8Tier 1 (unauth probe)inferred	−6
Total penalty					−6
Full unknown tax 213 — capped at 25 (point score uses 50% of the capped value)					−213
Evidence-graded tax (successes not live-verified by a Tier 2 probe) 34.4 — capped at 25 (point score uses 25% of the capped value)					−34.4
Raw score = 100 − 6 = 94 Point score = 94 − 50% × 25 − 25% × 25 = 75.3 → 75					75

inferred = detected from passive signals, not a directly observed interrupt — penalized at half weight

What would make this Easy

One concrete change per blocker found. These are the diffs between this listing's current parity and an unattended agent path.

Activate — CAPTCHA / bot-challengeDrop the CAPTCHA, or gate it behind a documented bot-detection signal a well-behaved agent can pass.

How we scored this

Confidence: Provisional (0.55) — Based on Tier 0/1 evidence only (passive checks, no live transaction attempt) — treat the number as a triage signal, not a verified outcome.
Machine-Readability sub-score: 47 / 100 (a separate integration-ease signal — it never enters the Interrupt Score or badge).
Some capability stages are not yet probed — shown plainly in the spine above, never as a pass.
Rubric, tiers, confidence model, and badge thresholds →

Machine-readability checks 47 / 100

Four check groups, equal weight: machine interfaces, browsing efficiency, element discoverability, and discovery/agent access. Each check carries an evidence grade (proven / plausible / emerging) — an honesty label that never weights the score. What these mean →

Unauthenticated API error is structured JSONplausibleFound — api.stripe.com/ (HTTP 404)
Unauthenticated API returns auth guidance (401/403 or documented)plausibleNot provided
API exposes rate-limit headersplausibleNot provided
API key obtainable without human interactionplausibleNot checked — API documentation host reachable (https://docs.stripe.com/) — reachability is not evidence of unattended key issuance
llms.txtemergingFound — docs.stripe.com/llms.txt (90.1 KB, 511 links)
llms-full.txtemergingNot provided
AGENTS.mdemergingNot provided
A2A agent cardemergingNot provided
MCP server (well-known or official registry)plausibleNot provided
OpenAPI/Swagger specplausibleNot provided
Rate-limit headersplausibleNot provided
Structured JSON error responsesplausibleNot provided
OAuth authorization-server metadata (RFC 8414)provenNot provided
API catalog (RFC 9727) (emerging)emergingNot provided
Agent-payment discovery (x402 / UCP) (emerging)emergingNot provided
Lean HTML transfer sizeplausibleNot provided
Manageable DOM sizeplausible1248 DOM nodes (threshold 1500)
High content-to-markup densityplausibleNot provided
Content readable without JS executionprovenraw HTML holds 93% of rendered text (8600 vs 9236 chars; threshold 40%)
Clean-content alternate (RSS/Atom/feed/markdown)plausibleNot provided
Serves markdown on Accept: text/markdownplausiblereturned text/markdown; charset=utf-8
Interactive elements are semanticplausibleNot provided
Form fields have accessible namesplausible1/1 named (100%)
Inputs carry autocomplete hintsplausibleNot provided
WebMCP tools (modelContext API)emerging4 tool(s) registered via the modelContext API during page load
AI retrieval/search fetchers allowed (robots.txt)provenno retrieval-fetcher blocks in robots.txt
Sitemap (indexability)plausibleFound — docs.stripe.com/sitemap.xml
schema.org JSON-LD in raw HTMLplausibleNot provided
Content-Signal directives (robots.txt)emergingai-train=yes, search=yes, ai-input=yes
Web Bot Auth key directory (emerging)emergingNot provided
Discovery Link headers on homepage (emerging)emergingrel=service-meta
Pricing visible without loginNot provided
robots.txt AI-crawler accessplausibleno AI-crawler blocks in robots.txt

Evidence & history

Last probed 2026-10-07 04:17 UTC. The raw JSON is the archival record.

Date	Score	Badge	Rubric version
2026-10-07 04:17 UTC	75	Moderate-Interrupt (current)	rubric v2026.4
2026-10-07 04:17 UTC	75	Moderate-Interrupt	rubric v2026.4
2026-09-07 01:51 UTC	69	Moderate-Interrupt	rubric v2026.4
2026-09-07 01:46 UTC	69	Moderate-Interrupt	rubric v2026.4
2026-08-09 23:47 UTC	69	Moderate-Interrupt	rubric v2026.4
2026-08-09 23:47 UTC	53	Moderate-Interrupt	rubric v2026.4
2026-08-09 17:13 UTC	51	Moderate-Interrupt	rubric v2026.4
2026-08-09 05:24 UTC	58	Moderate-Interrupt	rubric v2026.3
2026-08-09 05:24 UTC	58	Moderate-Interrupt	rubric v2026.3
2026-08-09 05:16 UTC	58	Moderate-Interrupt	rubric v2026.3
2026-08-09 05:16 UTC	58	Moderate-Interrupt	rubric v2026.3
2026-08-09 05:13 UTC	58	Moderate-Interrupt	rubric v2026.3
2026-08-09 05:13 UTC	88	Low-Interrupt	rubric v2026.3
2026-08-09 03:14 UTC	88	Low-Interrupt	rubric v2026.3
2026-08-09 01:48 UTC	88	Low-Interrupt	rubric v2026.2
2026-08-09 01:45 UTC	88	Low-Interrupt	rubric v2026.2
2026-07-10 07:16 UTC	100	Low-Interrupt	rubric v2026.1

Alternatives in Agent-Commerce Infrastructure

Other Agent-Commerce Infrastructure tools in the same mode (integrated), ranked by Overall LLM-Friendliness (the mean of Interrupt Score and Machine-Readability) — comparable to this listing because they share its usage mode.

Embed this rating

Copy this snippet to display your Interrupt Index seal on your site — the seal image and link stay in sync with your latest probe automatically. Pick the variant that matches your site’s theme.

Light (default)

<a href="https://interruptindex.com/tools/stripe-agent-toolkit-mcp-server"><img src="https://interruptindex.com/badge/stripe-agent-toolkit-mcp-server.svg" alt="Stripe Agent Toolkit MCP Server — Interrupt Index agent-readiness rating" height="64"></a>

Dark

<a href="https://interruptindex.com/tools/stripe-agent-toolkit-mcp-server"><img src="https://interruptindex.com/badge/stripe-agent-toolkit-mcp-server.svg?theme=dark" alt="Stripe Agent Toolkit MCP Server — Interrupt Index agent-readiness rating" height="64"></a>