Skip to content

Rank #3 of 4 in Mobile & In-Person Payments

SumUp logo

SumUp

SumUp Payments Limited · commercial

npm 6.4k/wknpm/wk -4.7k

Try itExperimental

See what an agent can do with SumUp before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$mcp-probe → https://mcp.sumup.com/mcplive — run just now from our edge
$ press ▶ run to send one JSON-RPC initialize from our edge
real JSON-RPC against the vendor’s documented MCP endpoint — read-only, nothing is written

Verified integrations

Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.

By theme — the product's score on each story themeBy theme

Accept payments — stories about accept payments in this arenaAccept paymentsevidence →

Stories about accept payments in this arena

36.9/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

36.4/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

7.2/100

Catalog receipts — stories about catalog receipts in this arenaCatalog receiptsevidence →

Stories about catalog receipts in this arena

0.0/100

Checkout integration — stories about checkout integration in this arenaCheckout integrationevidence →

Stories about checkout integration in this arena

65.3/100

Disputes refunds — stories about disputes refunds in this arenaDisputes refundsevidence →

Stories about disputes refunds in this arena

10.3/100

Hardware fleet — stories about hardware fleet in this arenaHardware fleetevidence →

Stories about hardware fleet in this arena

12.6/100

Offline reliability — stories about offline reliability in this arenaOffline reliabilityevidence →

Stories about offline reliability in this arena

80.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

8.6/100

Payouts reconciliation — stories about payouts reconciliation in this arenaPayouts reconciliationevidence →

Stories about payouts reconciliation in this arena

10.3/100

Pci compliance — stories about pci compliance in this arenaPci complianceevidence →

Stories about pci compliance in this arena

30.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3n/a0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial7/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10C

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1full8/10C

Accept chip, contactless, and mobile-wallet (Apple Pay / Google Pay) payments in person C

Payment methods

merchant-ops userAccept payments — stories about accept payments in this arenaAccept payments3full8/10C

Accept contactless card payments on an off-the-shelf phone (Tap to Pay) without buying a reader C

Tap to pay

founderAccept payments — stories about accept payments in this arenaAccept payments3full8/10C

Build a custom point-of-sale checkout that drives the terminal from my backend through a documented server-driven API C

Custom checkout

developerCheckout integration — stories about checkout integration in this arenaCheckout integration3full8/10T

Have an agent pull transactions and payouts via API and reconcile daily takings into my ledger C

Reconciliation

ai-native userPayouts reconciliation — stories about payouts reconciliation in this arenaPayouts reconciliation3partial4/10C

Manage a fleet of readers and terminals via API — register devices, monitor status, and update configuration remotely C

Fleet api

developerHardware fleet — stories about hardware fleet in this arenaHardware fleet3partial3/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3none0/10

Have an agent monitor dispute deadlines via API or webhooks and draft evidence responses for my review G

Disputes

ai-native userDisputes refunds — stories about disputes refunds in this arenaDisputes refunds3none0/10

Have an agent provision a new location end-to-end via API — creating the location and registering its readers C

Ai fleet ops

ai-native userHardware fleet — stories about hardware fleet in this arenaHardware fleet3none0/10

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3n/auntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3n/auntestednone yet

Sign up, get approved, and order hardware from the dashboard so I am taking in-person payments the same week C

Onboarding

founderAccept payments — stories about accept payments in this arenaAccept payments3noneuntestednone yet

Keep taking card payments when the internet drops, with transactions stored and forwarded when connectivity returns G

Offline

merchant-ops userOffline reliability — stories about offline reliability in this arenaOffline reliability2full8/10C

Test my in-person integration end-to-end with a simulated reader or test card environment before going live C

Testing

developerCheckout integration — stories about checkout integration in this arenaCheckout integration2full8/10C

Embed in-person payments into my own iOS or Android app with official mobile SDKs G

Custom checkout

developerCheckout integration — stories about checkout integration in this arenaCheckout integration2full7/10C

Issue full or partial refunds back to the original card from the point of sale, dashboard, or API C

Refunds

merchant-ops userDisputes refunds — stories about disputes refunds in this arenaDisputes refunds2partial6/10C

Pair a card reader with the POS app or register it to my account and take a payment within minutes C

Readers

merchant-ops userHardware fleet — stories about hardware fleet in this arenaHardware fleet2partial6/10C

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial5/10T

Keep my PCI scope minimal because card data is captured end-to-end by certified readers and vendor systems, with vendor guidance on my remaining obligations C

Pci

developerPci compliance — stories about pci compliance in this arenaPci compliance2partial5/10C

Subscribe to payment lifecycle events (authorized, captured, refunded, disputed) via webhooks to drive downstream automations G

Payment events

developerCheckout integration — stories about checkout integration in this arenaCheckout integration2partial4/10C

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial3/10C

Get notified of chargebacks and submit dispute evidence before the deadline C

Disputes

merchant-ops userDisputes refunds — stories about disputes refunds in this arenaDisputes refunds2none0/10

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Configure tipping prompts (percentages, smart amounts, custom tips) collected on the reader or terminal C

Tipping

merchant-ops userAccept payments — stories about accept payments in this arenaAccept payments2noneuntestednone yet

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Manage an item catalog with inventory counts that stay in sync across registers and channels C

Catalog

merchant-ops userCatalog receipts — stories about catalog receipts in this arenaCatalog receipts2noneuntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2n/auntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Reconcile daily takings against payouts with itemized transaction and fee reports C

Reconciliation

merchant-ops userPayouts reconciliation — stories about payouts reconciliation in this arenaPayouts reconciliation2noneuntestednone yet

Run multiple locations with per-location devices, settings, and reporting C

Multi location

merchant-ops userHardware fleet — stories about hardware fleet in this arenaHardware fleet2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2n/auntestednone yet

See when each payout lands and speed it up (next-day or instant) when I need the cash C

Payouts

founderPayouts reconciliation — stories about payouts reconciliation in this arenaPayouts reconciliation2noneuntestednone yet

Split a single sale across multiple payment methods or payers C

Payment methods

merchant-ops userAccept payments — stories about accept payments in this arenaAccept payments2noneuntestednone yet

Issue digital (email/SMS) or printed receipts that meet card-network requirements C

Receipts

merchant-ops userCatalog receipts — stories about catalog receipts in this arenaCatalog receipts1none0/10

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1n/auntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 33 stories with headroom

What would move SumUp’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productDelegate tasks to a built-in AI assistant inside the product

    nonemoves Built-in AIimpact 45

    SumUp's evidence only shows it exposes an MCP server and Agent Toolkit so that external AI agents/coding assistants can call SumUp APIs — this is SumUp acting as a tool provider for other agents, not a built-in AI assistant embedded in the SumUp product itself that a user can delegate tasks to.

  2. Disputes refunds — stories about disputes refunds in this arenaHave an agent monitor dispute deadlines via API or webhooks and draft evidence responses for my review

    nonemoves PA Scoreimpact 30

    SumUp's docs cover checkouts, refunds, webhooks for checkout status, and MCP/agent tooling, but there is no evidence of a disputes/chargebacks API, dispute deadline data, or evidence-submission endpoints that an agent could monitor or draft responses against.

  3. Hardware fleet — stories about hardware fleet in this arenaHave an agent provision a new location end-to-end via API — creating the location and registering its readers

    nonemoves PA Scoreimpact 30

    Missing: location creation API, reader-to-location registration endpoint, any end-to-end provisioning example.

  4. Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events

    nonemoves PA Scoreimpact 30

    SumUp's docs show only basic webhook notifications for checkout status changes (via return_url), not a rules engine allowing users to define custom conditions/actions across events; no evidence of any automation/rules builder.

  5. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    SumUp is a payments platform holding transaction/merchant data, and the evidence pack has no mention of any data export feature (open formats like CSV/JSON export of transactions, merchant data, or account closure/data portability tooling); it covers payment APIs, MCP/agent tooling, and checkout flows but nothing about exporting user data and leaving.

  6. Accept payments — stories about accept payments in this arenaSign up, get approved, and order hardware from the dashboard so I am taking in-person payments the same week

    nonemoves PA Scoreimpact 30

    The evidence pack is entirely developer-API documentation (checkouts, SDKs, MCP servers, cloud API, refunds) and pricing claims; it contains no evidence about the merchant signup/approval workflow or ordering hardware from a dashboard, which is the core of this founder-onboarding story.

  7. Agenticness — how well agents can access and operate the productSet up automations that run autonomously in the background

    nonemoves Built-in AIimpact 30

    SumUp is a payments API/platform with webhooks, an MCP server, and an agent toolkit for building agentic integrations, but there is no evidence of a native automation/workflow feature that runs autonomously in the background (e.g., scheduled jobs, triggers, rules engine) within SumUp itself — it only exposes APIs/tools that a third party would need to orchestrate.

  8. Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent

    nonemoves agent-readyimpact 30

    SumUp docs describe API keys as static, account-wide credentials ('act on behalf of the merchant account that created the key') with no mention of scopes, permissions, or least-privilege options for agents or sub-credentials.

Showing the top 8 of 33 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map8 surfaces · 22 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

5 of 16 testable claims verified · 2 contradictedintegrity 6/100

25 distinct capability claims found in SumUp’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

5

Verified

9

Unverified

2

Contradicted

8

Undersold

Verified (10)
Unverified (14)
Contradicted (2)
Undersold (8)
Claims outside our story set (4)

Real capability claims found in SumUp’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • Uses static API keys that let an application act on behalf of the merchant account that created them

    source ↗
  • No monthly minimums or hidden fees on the pricing plans

    source ↗
  • Higher-tier plan adds customer rewards, automated marketing, and monthly promotions beyond POS

    source ↗
  • Money-back guarantee protects merchant funds when investing in SumUp products

    source ↗
Suggest a story for these →

Business model

usage-basedhardware-attach

Flat per-transaction fees (from 2.6% + 10¢ in-person US) with no monthly subscription; card readers are bought upfront at low one-time prices.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score27 (Sep 3 '26)24 (Sep 16 '26)
Agent-ready56 (Sep 3 '26)58 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

Data

Agent surface uptime MCP 100% · llms.txt 100% (30d, checked every 6h since Sep 8 '26)