Square

# Fix list: Square

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/square, the October 2026 research run, assessed 8 October 2026. Grade B, 69.2 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 Square: 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, 58 out of 100, up to 8.4 more on the total

Why it scored 58: Graded on the hosted REST API. Status page at issquareup.com with an incident history, though its components endpoint returns an empty list (20). In the 90 days to 8 October 2026 the page lists 15 incidents, all labelled minor. One, on 27 September, reported widespread elevated latency and service errors across Square, including payment authorisation and refunds, and closed 1 hour 47 minutes after the first post. The others were partial, by card network, device or feature (10). No numeric limits were found for the REST API, and the docs say endpoints might enforce different limits. GraphQL is limited to 10 queries a second (5). The docs describe 429 `RATE_LIMITED` errors, exponential backoff with jitter and idempotency keys on writes (15). No SLA found in the developer terms or docs (0). The REST API is generally available, but 97 of 332 operations in the spec are beta and the MCP server is beta (8).

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. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 found in the docs index or the spec (0). Fees are public without login. The API has no charge, and card payments through the payments APIs cost 2.9% + 30 cents in the US (20). The sandbox is free, and the Square Free plan is $0 a month (20). A person must create a Square account and an application in the Developer Console, or approve OAuth in a browser (0).

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.

## 3. Security & auth, 67 out of 100, up to 5.8 more on the total

Why it scored 67: OAuth with code and PKCE flows, read and write scopes for each resource, 30-day access tokens, refresh and revocation. The remote MCP server uses OAuth with registration limited to an allowlist of clients and advertises 48 scopes. Personal access tokens are unrestricted (26). Read-only scopes, and `DISALLOW_WRITES` on the local MCP server. No confirmation step for destructive calls was found (12). The API returns seller and customer text. The MCP page advises testing prompts in the sandbox, and no prompt-injection guidance was found (3). API Logs show each request and response for 28 days, with webhook event logs (12). A Bugcrowd programme is linked from the security page, which states ISO 27001 and PCI certification. squareup.com and developer.squareup.com return 404 for security.txt, and the Bugcrowd and trust centre pages didn't render for us (14).

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.

## 4. Agent ergonomics, 83 out of 100, up to 2.8 more on the total

Why it scored 83: List endpoints take `limit` and a cursor, and GraphQL selects fields for reads. The MCP server has three tools that load service and type detail on request (20). Cursor pagination, search endpoints with filters, and batch endpoints. Cursors expire after 5 minutes (18). Errors carry a category, a code and the request field at fault (18). Idempotency keys on 78 request schemas and optimistic concurrency by version. The MCP tools carry no readOnlyHint or destructiveHint annotations in the source (14). Official SDKs in seven languages. An MCP call needs two discovery calls first (13).

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. Transparency & trust, 70 out of 100, up to 2.6 more on the total

Made of editorial 56, provenance 84.

Why it scored 70: Closed service under published developer terms. The API spec and MCP server are Apache 2.0 and the Node.js SDK is MIT (15). The privacy notice was updated on 15 September 2026 and says retention is decided case by case, with no periods given. No public DPA was found at the addresses we tried (13). APIs are typically deprecated at least 12 months before retirement, retired endpoints return 410, and deprecated items are listed with dates (20). The privacy notice names categories of service providers and processing in the US, Japan, the UK and the EU. No named sub-processor list was found (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):

- Terms of service: read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points (5.1 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 87 out of 100, up to 2.1 more on the total

Why it scored 87: Public OpenAPI 3.0 spec in square/connect-api-specification with 332 operations and 1,476 schemas (25). developer.squareup.com/llms.txt indexes the docs and links llms-full.txt (10). 327 of 332 operations carry a description stating purpose, with little guidance on when not to use one (14). Request schemas are typed, 204 schemas are enums and required fields are marked. The MCP tool `make_api_request` takes an untyped request object, with types fetched through `get_type_info` (12). Errors are documented as category, code, detail and field with a published code list, but the spec lists only 200 responses and names endpoint errors on 82 of 332 operations (11). Dated API versions set by the `Square-Version` header and monthly release notes (15).

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.

## 7. Maintenance & community, 81 out of 100, up to 1.7 more on the total

Why it scored 81: API version 2026-09-16 was released 22 days before the check (30). Three dated releases in 90 days, on 15 July, 19 August and 16 September 2026 (20). Public release notes, a developer forum and a Discord community are linked from the docs. GitHub issues were not readable, and the MCP server repository has one commit since May 2025 (10). Seven official SDKs were regenerated for 2026-09-16, the Node.js one at 46.0.0. No Square server appears in the official MCP registry (15). The Node.js SDK has CI and integration workflows. The npm package square-mcp-server is still 0.1.2, published in April 2025 (6).

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.

## 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.

- unchecked: the tool list of the remote MCP server at mcp.squareup.com, which answers 401 without an OAuth token. The three tools are read from the open-source local server
- unchecked: GitHub stars and open issues, because the GitHub API refused us for its rate limit
- unchecked: the Bugcrowd programme page and trust.squareup.com, which render with JavaScript only
- unchecked: whether Square publishes a DPA or a named sub-processor list. Two guessed addresses returned 404 and the privacy notice links neither
- No numeric REST rate limits and no SLA were found in the reviewed documentation
- The MCP README gives https://mcp.squareup.com/sse and the docs give https://mcp.squareup.com/mcp. Both answered 401 on 8 October 2026
- Whether creating a Square account needs a card was not checked. The sandbox is documented as free
- The category fits the catalogue, orders and payment-link APIs. Square is also a payment processor, so the payments category would be a reasonable second home

## Weaknesses

- The MCP server is marked beta, and the remote server reaches production data only
- No numeric rate limits were found for the REST API. Only GraphQL states a figure, 10 queries a second
- No SLA was found in the developer terms or documentation
- The status page recorded widespread latency and errors on 27 September 2026, including payment authorisation
- A personal access token grants unrestricted access to the whole Square account
- 97 of the 332 operations in the spec are marked beta

## 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.

- Test against the sandbox first with the local MCP server and `SANDBOX=true`. The remote server at mcp.squareup.com reaches production only
- Set `DISALLOW_WRITES=true` on the local MCP server when the task only reads
- Call `get_service_info`, then `get_type_info`, before each `make_api_request`. The request body is otherwise untyped
- Send a fresh `idempotency_key` on every write, and reuse it when retrying the same write
- Pin `Square-Version` in each request. Use a page cursor within 5 minutes of receiving it

## 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.