{
  "fixes": {
    "slug": "shippypro",
    "name": "ShippyPro",
    "listing": "https://www.anchorterminal.com/tools/shippypro",
    "markdown": "# Fix list: ShippyPro\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/shippypro, the October 2026 research run, assessed 9 October 2026. Grade D, 48.7 out of 100.\n\nThis 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.\n\nFor a coding agent working on ShippyPro: 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.\n\n## 1. Payments \u0026 pricing, 5 out of 100, up to 11.9 more on the total\n\nWhy it scored 5: No x402, MPP or L402 (0). The self-serve plans have public monthly prices, but the pricing page marks them UI only and lists API access under Enterprise at a custom price through sales (0). The terms describe a 14-day, 30-order trial with no card. The help centre says APIs are activated by sales on an Enterprise plan, so we could not establish that a trial account can call the API, and give part credit (5 of 20). A person signs up in a browser and sales activates the API (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 2. Agent ergonomics, 46 out of 100, up to 8.8 more on the total\n\nWhy it scored 46: Scored on the REST API. v1 report calls take date ranges and switches such as `IncludeItems`, with no field selection, and v2 lists take `pageSize` up to 100 (12 of 25). v1 lists have date filters and no pagination. v2 has cursor pagination and filters by carrier and country (10 of 20). v1 mixes HTTP status codes with 200 responses carrying `Status` 2, though `ErrorType` and `ErrorSuggestion` name a cause and a fix. v2 errors are application/problem+json with field pointers (12 of 20). No idempotency key on `Ship`, `Edit` or `VoidShipments`. v2 accepts `Idempotency-Key` on POST and DELETE and answers 409 on a mismatched replay (7 of 20). `Ship` has eight required parameters and needs a `CarrierID` from the panel or `GetCarriers`. No official SDK was found on the pages read, though the API page's FAQ mentions SDKs (5 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 3. Security \u0026 auth, 51 out of 100, up to 8.6 more on the total\n\nWhy it scored 51: API keys are created in the panel, several per account, in three types (Full Access, Maps, PII Excluded), and v2 answers 401 for a revoked key. No expiry or rotation was found. The help centre still describes Basic auth with the key as username (22 of 30). The Maps and PII Excluded types narrow a key, but there is no read-only key and no confirmation step for label creation or voiding. The Generic carrier allows tests without a real shipment (8 of 20). Tracking messages and marketplace order text come from third parties, and no guidance on untrusted content was found. Requests are screened for script-like strings (3 of 15). The panel has API logs with requests and responses, an API error history and webhook logs (10 of 15). The site footer states ISO 27001 and SOC 2 Type II, with no certificate, report or trust page found. security.txt was not requested because robots.txt disallows the path. No bug bounty or disclosure policy was found (8 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 4. Maintenance \u0026 community, 25 out of 100, up to 6.6 more on the total\n\nWhy it scored 25: No API changelog or dated release notes were found. Both OpenAPI files were last modified on 8 October 2026 per their HTTP headers, and the v2 file reads as recent work, so we give half for recency on that metadata alone (15 of 30). No dated entries in the last 90 days (0). Closed service with no changelog. Support runs through tickets, email and chat, the SLA sets response times, and the status page is updated daily (7 of 15). No official SDK or MCP registry entry was found (0). The contract is current OpenAPI 3.1 with examples (3 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 5. Reliability, 70 out of 100, up to 6 more on the total\n\nWhy it scored 70: Read with the hosted lines and scored on the v1 REST API, where rates, labels and tracking live. Statuspage at status.shippypro.com with a component for ShippyPro API \u0026 Webhooks and one per carrier (20). From 11 July to 8 October 2026 no entry names the API. A platform login problem ran for 3 hours 6 minutes on 18 September, marked critical, SMS one-time codes went unsent from 29 August to 3 September and from 19 September to 5 October, and one carrier's label creation was marked critical on most days, some for several days (Asendia from 20 to 31 August). We read that as one major, as for other listings in this category (10 of 30). 20 requests every 10 seconds (15). v1 documents the 429 and nothing more, and `Ship` takes no idempotency key. The help centre suggests spreading calls over several IP addresses. v2 documents `Retry-After`, rate-limit headers and `Idempotency-Key`, but covers no shipping call (5 of 15). The SLA commits to 99.5 per cent a month with service credits (10). GA (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 6. Schema \u0026 documentation, 64 out of 100, up to 5.9 more on the total\n\nWhy it scored 64: OpenAPI 3.1 files for v1 (55 operations, 119 schemas) and v2 (17 operations), loaded by the reference at api.shippypro.com/docs (25). api.shippypro.com/llms.txt returns 404, the main site's robots.txt disallows /llms.txt so it was not requested, and no Markdown docs were found (0). v1 descriptions state purpose, how to test and known traps, such as `GetTracking` not being meant for bulk use (14 of 20). Required fields are marked, but the v1 file has 14 enums in all, `LabelURL` is a string or an array, `delivery_days` a number or a string, and carrier options are free name and value pairs (9 of 15). 812 examples in the v1 file. v1 error responses are one line per status code with no body schema, and v2 documents RFC 9457 problem types (10 of 15). Versions are in the path, v1 and v2. No changelog was found (6 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## 7. Transparency \u0026 trust, 58 out of 100, up to 3.7 more on the total\n\nMade of editorial 48, provenance 68.\n\nWhy it scored 58: Closed service. The Terms \u0026 Conditions are public and name the contracting entity, but carry no date and reserve the right to change the agreement, prices and service without notice (12 of 30). The privacy policy covers shipment sender and recipient data per product area, anonymises Amazon customer data 30 days after delivery, keeps staff impersonation logs for 19 months and says personal data is never sold. General retention is stated only as long as necessary, and no DPA was found (18 of 30). No deprecation policy. The terms allow any service to be discontinued without notice. The status page carried dated carrier notices (TNT Italy on 13 July, Deutsche Post on 17 August 2026), and the SLA promises seven days' notice of planned downtime (6 of 20). Sub-processors are named per product area, and the full list with countries is a PDF whose file name is dated 15 September 2022, which we did not read (12 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: shippypro.com, registered 2016-10-24 (9 years) (11 of 15)\n- Terms of service: read, states 2 of the 7 things a reader expects, and has 1 clause that costs points (3.7 of 10)\n- Privacy policy: read, states 6 of the 8 things a reader expects (8.5 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: could not be fetched (0 of 10)\n\n## What we couldn't check\n\nWhat 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.\n\n- unchecked: www.shippypro.com/.well-known/security.txt and /llms.txt, which the site's robots.txt disallows, so neither was requested\n- unchecked: the full sub-processor list, a PDF on public-website-hb.shippypro.com that the privacy policy links (file name dated 15 September 2022)\n- unchecked: official SDKs or repositories. None is linked from the pages read. One PyPI lookup was made before reading PyPI's robots.txt, which disallows that path, and its result was discarded\n- unchecked: prices in USD and GBP. The pricing page was read in EUR only\n- Whether a 14-day trial account can create an API key and call the API. The OpenAPI file says to create a free account, and the help centre says APIs need an Enterprise plan activated by sales\n- Whether the API accepts Basic auth as the help centre says, Bearer as the OpenAPI files say, or both\n- Whether v1 returns Retry-After on a 429. The v1 file does not say\n- Whether ISO 27001 and SOC 2 Type II reports are available. The footer states both and no report or trust page was found\n- When the v2 API launched and whether v1 has an end date. No changelog or deprecation notice was found\n- The lead named https://www.shippypro.com/en/api as the docs. That is the product page, and the reference is at https://api.shippypro.com/docs\n\n## Weaknesses\n\n- The help centre says APIs can only be activated with an Enterprise plan, which has no public price and starts with sales\n- No API changelog, release notes or deprecation policy was found, and the terms allow changes without notice\n- `POST /v1/Ship` takes no idempotency key. Only the 17 v2 operations accept `Idempotency-Key`\n- Carrier label incidents marked critical appear on the status page on most days from August to October 2026\n- No official SDK, MCP server or llms.txt was found on the pages read\n- v1 answers some failures with HTTP 200 and `Status` 2, and `LabelURL` can be a string or an array\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Send `Authorization: Bearer \u003cAPI key\u003e` and POST a JSON body with `Method` and `Params` to `https://api.shippypro.com/v1/\u003cMethod\u003e`. Parameter names are case-sensitive\n- Check `Status` and `ErrorMessage` in every `Ship` response. HTTP 200 with `Status` 2 means no label was created\n- Before retrying a failed `Ship` call, look the order up by `TransactionID`. v1 has no idempotency key, and each label counts against the plan\n- Test with the Generic carrier. `Ship` and `Edit` calls on a real carrier create real labels\n- Stay under 20 calls per 10 seconds, and use webhooks for tracking. The docs advise against `GetTracking` in bulk\n\n## When it's done\n\nSend 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.\n",
    "grade": "D",
    "score": 48.7,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 5,
        "maxGain": 11.9,
        "reason": "No x402, MPP or L402 (0). The self-serve plans have public monthly prices, but the pricing page marks them UI only and lists API access under Enterprise at a custom price through sales (0). The terms describe a 14-day, 30-order trial with no card. The help centre says APIs are activated by sales on an Enterprise plan, so we could not establish that a trial account can call the API, and give part credit (5 of 20). A person signs up in a browser and sales activates the API (0).",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 46,
        "maxGain": 8.8,
        "reason": "Scored on the REST API. v1 report calls take date ranges and switches such as `IncludeItems`, with no field selection, and v2 lists take `pageSize` up to 100 (12 of 25). v1 lists have date filters and no pagination. v2 has cursor pagination and filters by carrier and country (10 of 20). v1 mixes HTTP status codes with 200 responses carrying `Status` 2, though `ErrorType` and `ErrorSuggestion` name a cause and a fix. v2 errors are application/problem+json with field pointers (12 of 20). No idempotency key on `Ship`, `Edit` or `VoidShipments`. v2 accepts `Idempotency-Key` on POST and DELETE and answers 409 on a mismatched replay (7 of 20). `Ship` has eight required parameters and needs a `CarrierID` from the panel or `GetCarriers`. No official SDK was found on the pages read, though the API page's FAQ mentions SDKs (5 of 15).",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 51,
        "maxGain": 8.6,
        "reason": "API keys are created in the panel, several per account, in three types (Full Access, Maps, PII Excluded), and v2 answers 401 for a revoked key. No expiry or rotation was found. The help centre still describes Basic auth with the key as username (22 of 30). The Maps and PII Excluded types narrow a key, but there is no read-only key and no confirmation step for label creation or voiding. The Generic carrier allows tests without a real shipment (8 of 20). Tracking messages and marketplace order text come from third parties, and no guidance on untrusted content was found. Requests are screened for script-like strings (3 of 15). The panel has API logs with requests and responses, an API error history and webhook logs (10 of 15). The site footer states ISO 27001 and SOC 2 Type II, with no certificate, report or trust page found. security.txt was not requested because robots.txt disallows the path. No bug bounty or disclosure policy was found (8 of 20).",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 25,
        "maxGain": 6.6,
        "reason": "No API changelog or dated release notes were found. Both OpenAPI files were last modified on 8 October 2026 per their HTTP headers, and the v2 file reads as recent work, so we give half for recency on that metadata alone (15 of 30). No dated entries in the last 90 days (0). Closed service with no changelog. Support runs through tickets, email and chat, the SLA sets response times, and the status page is updated daily (7 of 15). No official SDK or MCP registry entry was found (0). The contract is current OpenAPI 3.1 with examples (3 of 10).",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 70,
        "maxGain": 6,
        "reason": "Read with the hosted lines and scored on the v1 REST API, where rates, labels and tracking live. Statuspage at status.shippypro.com with a component for ShippyPro API \u0026 Webhooks and one per carrier (20). From 11 July to 8 October 2026 no entry names the API. A platform login problem ran for 3 hours 6 minutes on 18 September, marked critical, SMS one-time codes went unsent from 29 August to 3 September and from 19 September to 5 October, and one carrier's label creation was marked critical on most days, some for several days (Asendia from 20 to 31 August). We read that as one major, as for other listings in this category (10 of 30). 20 requests every 10 seconds (15). v1 documents the 429 and nothing more, and `Ship` takes no idempotency key. The help centre suggests spreading calls over several IP addresses. v2 documents `Retry-After`, rate-limit headers and `Idempotency-Key`, but covers no shipping call (5 of 15). The SLA commits to 99.5 per cent a month with service credits (10). GA (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 64,
        "maxGain": 5.9,
        "reason": "OpenAPI 3.1 files for v1 (55 operations, 119 schemas) and v2 (17 operations), loaded by the reference at api.shippypro.com/docs (25). api.shippypro.com/llms.txt returns 404, the main site's robots.txt disallows /llms.txt so it was not requested, and no Markdown docs were found (0). v1 descriptions state purpose, how to test and known traps, such as `GetTracking` not being meant for bulk use (14 of 20). Required fields are marked, but the v1 file has 14 enums in all, `LabelURL` is a string or an array, `delivery_days` a number or a string, and carrier options are free name and value pairs (9 of 15). 812 examples in the v1 file. v1 error responses are one line per status code with no body schema, and v2 documents RFC 9457 problem types (10 of 15). Versions are in the path, v1 and v2. No changelog was found (6 of 15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 58,
        "maxGain": 3.7,
        "reason": "Closed service. The Terms \u0026 Conditions are public and name the contracting entity, but carry no date and reserve the right to change the agreement, prices and service without notice (12 of 30). The privacy policy covers shipment sender and recipient data per product area, anonymises Amazon customer data 30 days after delivery, keeps staff impersonation logs for 19 months and says personal data is never sold. General retention is stated only as long as necessary, and no DPA was found (18 of 30). No deprecation policy. The terms allow any service to be discontinued without notice. The status page carried dated carrier notices (TNT Italy on 13 July, Deutsche Post on 17 August 2026), and the SLA promises seven days' notice of planned downtime (6 of 20). Sub-processors are named per product area, and the full list with countries is a PDF whose file name is dated 15 September 2022, which we did not read (12 of 20).",
        "blend": "editorial 48, provenance 68",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "shippypro.com, registered 2016-10-24 (9 years)",
        "points": 11,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 2 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 3.7,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 6 of the 8 things a reader expects",
        "points": 8.5,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "could not be fetched",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: www.shippypro.com/.well-known/security.txt and /llms.txt, which the site's robots.txt disallows, so neither was requested",
      "unchecked: the full sub-processor list, a PDF on public-website-hb.shippypro.com that the privacy policy links (file name dated 15 September 2022)",
      "unchecked: official SDKs or repositories. None is linked from the pages read. One PyPI lookup was made before reading PyPI's robots.txt, which disallows that path, and its result was discarded",
      "unchecked: prices in USD and GBP. The pricing page was read in EUR only",
      "Whether a 14-day trial account can create an API key and call the API. The OpenAPI file says to create a free account, and the help centre says APIs need an Enterprise plan activated by sales",
      "Whether the API accepts Basic auth as the help centre says, Bearer as the OpenAPI files say, or both",
      "Whether v1 returns Retry-After on a 429. The v1 file does not say",
      "Whether ISO 27001 and SOC 2 Type II reports are available. The footer states both and no report or trust page was found",
      "When the v2 API launched and whether v1 has an end date. No changelog or deprecation notice was found",
      "The lead named https://www.shippypro.com/en/api as the docs. That is the product page, and the reference is at https://api.shippypro.com/docs"
    ],
    "weaknesses": [
      "The help centre says APIs can only be activated with an Enterprise plan, which has no public price and starts with sales",
      "No API changelog, release notes or deprecation policy was found, and the terms allow changes without notice",
      "`POST /v1/Ship` takes no idempotency key. Only the 17 v2 operations accept `Idempotency-Key`",
      "Carrier label incidents marked critical appear on the status page on most days from August to October 2026",
      "No official SDK, MCP server or llms.txt was found on the pages read",
      "v1 answers some failures with HTTP 200 and `Status` 2, and `LabelURL` can be a string or an array"
    ],
    "agentNotes": [
      "Send `Authorization: Bearer \u003cAPI key\u003e` and POST a JSON body with `Method` and `Params` to `https://api.shippypro.com/v1/\u003cMethod\u003e`. Parameter names are case-sensitive",
      "Check `Status` and `ErrorMessage` in every `Ship` response. HTTP 200 with `Status` 2 means no label was created",
      "Before retrying a failed `Ship` call, look the order up by `TransactionID`. v1 has no idempotency key, and each label counts against the plan",
      "Test with the Generic carrier. `Ship` and `Edit` calls on a real carrier create real labels",
      "Stay under 20 calls per 10 seconds, and use webhooks for tracking. The docs advise against `GetTracking` in bulk"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-09",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}