Sendcloud

# Fix list: Sendcloud

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/sendcloud, the October 2026 research run, assessed 7 October 2026. Grade B, 62 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 Sendcloud: 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. Security & auth, 49 out of 100, up to 8.9 more on the total

Why it scored 49: A key pair per API integration, usable as Basic or exchanged for a one-hour Bearer token, and OAuth with PKCE for MCP. The only scope is `api`, which covers the whole account (20). No read-only credential found. The MCP toolset filter is enforced on the server, and annotations let a client prompt before creates and cancels (8). Responses carry text written by others, such as addresses, order data and support tickets. The MCP page says results are reference information only and gives no injection guidance (3). Integration exception logs are in the API. No per-call audit view found (3). ISO/IEC 27001:2022, annual penetration tests, a private HackerOne programme and a disclosure address. No security.txt and no SOC 2 found (15).

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.

## 2. Payments & pricing, 37 out of 100, up to 7.9 more on the total

Why it scored 37: No x402, MPP or L402 (0). Plan prices and per-label fees are public in euros, from €28 a month plus €0.10 a label to €639 plus €0.07, with sample carrier rates. We couldn't read which plans the API access row covers (17). A Free plan for 20 parcels a month and a 14-day trial, both stated as needing no card, plus free Unstamped letter test labels (20). A person signs up in a browser, adds an invoice address and creates the keys in the panel (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. Reliability, 68 out of 100, up to 6.4 more on the total

Why it scored 68: Graded on API v3 and the hosted MCP server, with the hosted lines. Statuspage at status.sendcloud.com with components for the API, the panel and each carrier and integration (20). 25 incidents between 8 July and 7 October 2026. Twelve are marked major or critical and each concerns one carrier's label announcements, mostly labelled third-party. Platform-side entries are minor, the longest a four-hour integration connection problem on 14 September and 94 minutes of label announcement issues across several carriers on 8 September. None names the Sendcloud API component, so we scored between minor-only and one major (15). Limits published, 1,000 safe and 100 unsafe requests a minute with a burst of 15 a second (15). 429 is documented without Retry-After or backoff guidance. A repeated `external_reference_id` returns the existing shipment (8). The home page claims 99.99 per cent uptime, and no SLA document was found (0). API v3 is the current version and the MCP page carries no beta label (10).

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.

## 4. Agent ergonomics, 71 out of 100, up to 4.7 more on the total

Why it scored 71: The MCP server makes one tool per operation, about 98 by the specs for its 24 toolsets, all on by default, which scores 5, and a `?toolsets=` filter enforced on calls adds 10. The API has `page_size` and no field selection (15). Cursor pagination through Link headers and filters by status, tracking number, reference and dates on shipments (18). JSON:API errors, though a carrier failure on a synchronous announce arrives in an `errors` array inside a success response (15). `external_reference_id` deduplicates shipment creation, and the docs say tools carry read-only, idempotent and destructive hints by HTTP method, which we couldn't confirm without an account (16). Shipping rules and defaults cut required fields. No official SDK was found (7).

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. Maintenance & community, 67 out of 100, up to 2.9 more on the total

Why it scored 67: Latest API v3 changelog entry 5 October 2026 (30). 37 dated entries between 9 July and 5 October (20). Closed service with a dated changelog and a help centre with email and chat support. No developer forum or public issue tracker found (9). The MCP server isn't in the official MCP registry, and no official SDK was found. A public Postman workspace exists (3). No packages to assess. The specs change with the changelog (5).

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.

## 6. Transparency & trust, 72 out of 100, up to 2.5 more on the total

Made of editorial 62, provenance 81.

Why it scored 72: Closed service with terms dated 1 September 2026 naming Sendcloud B.V. and four country entities (15). The privacy policy keeps server logs for at most 7 days and contact forms for 6 years. The DPA deletes customers' order data within 365 days of shipment completion and gives 30 days' notice of new sub-processors. Neither page showed a version date we could read (22). API v2 maintenance mode announced for April 2026, and one endpoint deprecated with a date (9 June 2026). Other deprecated fields are to go "in a future version", and no notice-period policy was found (10). Trust centre names five sub-processors, and the security page names AWS EU Central and EU North (15).

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 5 of the 7 things a reader expects, and has 3 clauses that cost points (2.3 of 10)
- Privacy policy: read, states 6 of the 8 things a reader expects (8.5 of 10)
- security.txt: not found (0 of 10)

## 7. Schema & documentation, 89 out of 100, up to 1.8 more on the total

Why it scored 89: 29 OpenAPI 3.1 specs for API v3, 104 operations, linked from llms.txt (25). llms.txt and a Markdown copy of every docs page (10). Every operation has a description. Some state limits, such as when a cancellation is rejected, and many are one sentence. MCP tools take their text from the same specs (13). 243 enums, required fields and maxima such as `page_size` up to 100 (13). 216 example blocks and JSON:API error objects with `status`, `code` and `detail`. 429 responses appear only in the Support API spec (13). Versioned v2 and v3 with a dated v3 changelog of 155 entries back to 25 May 2023 (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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 21 and 25 September 2026. The API v3 changelog records `insurance.currency` and `insurance.value` removed from POST /parcels/tracking, and `status_code`, `status_description` and `sub_status_code` removed from tracking event responses, with no earlier deprecation entry for those fields. The changes are documented on the day, so the deduction is the minimum (https://sendcloud.dev/api/v3/changelog.md)

## 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: which plans include API access. The pricing table has the row, and its per-plan marks didn't survive our reader
- unchecked: the live MCP tool list, tool count and annotations, which need an account. About 98 tools is our count from the specs
- unchecked: effective dates of the privacy policy and the DPA
- Whether the September 2026 field removals changed live responses or corrected the specs to match them
- Whether a payment method is required before the first paid label on the Free plan
- Whether an SLA exists on Enterprise, and whether Sendcloud keeps official SDKs or a public GitHub organisation (github.com was not reachable from our shell)
- Home-page figures (170+ carriers, 30,000+ merchants, 99.99 per cent uptime) are Sendcloud's claims

## Weaknesses

- One OAuth scope, `api`, and key pairs with full account access. No read-only credential was found in the reviewed documentation
- Changelog entries of 21 and 25 September 2026 record removed request and response fields on parcel tracking with no earlier deprecation entry
- No Retry-After header or backoff guidance was found for 429 responses
- No official SDK was found in the reviewed documentation, and the MCP server isn't in the official MCP registry
- No test environment. Labels other than the Unstamped letter options are charged unless the carrier accepts a cancellation

## 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.

- Use API v3 at https://panel.sendcloud.sc/api/v3. The v2 create-parcel endpoint is closed to accounts created from April 2026
- Test with `shipping_option_code` `sendcloud:letter` (returns use `sendcloud:letterreturn`). Any other label is billed unless cancelled within the carrier's deadline
- Set `external_reference_id` on every shipment so a retry returns the existing shipment (409) instead of a second label
- Read the `errors` array on synchronous announce responses. A carrier failure can arrive inside a success status
- Connect MCP with `?toolsets=shipments,shipping-options,parcel-tracking,returns` to keep the tool list short. Create and cancel tools act on the live account

## 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.