ShipBob

# Fix list: ShipBob

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/shipbob, the October 2026 research run, assessed 8 October 2026. Grade C, 60.8 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 ShipBob: 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. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). The pricing page lists the fee types (implementation, receiving, storage, pick, pack and ship) with no figures and a quote form (0). An account is free until physical inventory arrives, per the developer docs, and the sandbox is free and takes a test card number. We didn't open an account to confirm (20). A person signs up in a browser and creates the token or approves OAuth. Dynamic client registration on the MCP server still ends in a browser sign-in (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.

## 2. Security & auth, 55 out of 100, up to 7.9 more on the total

Why it scored 55: OAuth 2.0 authorisation code grant with PKCE, read and write scopes per domain, one-hour access tokens, 30-day refresh tokens rotated on use, and a revocation endpoint. The MCP server adds dynamic client registration. Personal Access Tokens have every scope and no expiry, and can be revoked (27 of 30). An OAuth app can ask for read scopes only, MCP writes are limited to the channel created at consent, and inventory is read-only over MCP. A token has no read-only option, and no confirmation step for cancels was found (12 of 20). Orders, addresses, gift messages and return notes are written by third parties. The MCP security page covers token handling and consent, with nothing on injected text (3 of 15). No log of API calls for the operator was found. Shipment logs record warehouse events (2 of 15). The trust page says SOC 2 and ISO 27001 audits are complete and lists penetration testing. No security.txt, disclosure policy or bug bounty was found (11 of 20).

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.

## 3. Agent ergonomics, 56 out of 100, up to 7.2 more on the total

Why it scored 56: Scored on the REST API, with the MCP server noted. Lists take a page size (up to 250 on products) but there's no field selection, and an order returns every shipment and line. The MCP server has 73 tools, with no toolsets or read-only subset documented (13 of 25). Page or cursor pagination on every list, a `next-page` response header, and filters by date, reference ID, tracking state and SKU. Two pagination styles are in use (16 of 20). A status code table, 422 for a duplicate reference ID and 410 with `api_version_deprecated` for a retired version. Error bodies are not uniform (12 of 20). Unique `reference_id` per channel on creates, and bulk hold and release are described as idempotent. No idempotency key. The MCP tool annotations sit behind sign-in and weren't read (10 of 20). No official SDK was found, and every write needs a `shipbob_channel_id` header looked up first (5 of 15).

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.

## 4. Maintenance & community, 41 out of 100, up to 5.2 more on the total

Why it scored 41: API version 2026-07 was released on 31 July 2026, 69 days before the check (20 of 30). The release notes have two entries under July 2026, the 2026-07 version and PKCE, and the second has no day, so it can't be placed inside the 90 days. The tutorials repository had four commits from 17 to 20 August. We gave half for this line (10 of 20). Closed service with dated release notes and a support address that promises a first reply within one business day (9 of 15). The MCP server isn't in the official registry, and no official SDK was found (0 of 15). OpenAPI specs are kept for each version. Nothing else to judge package health on (2 of 10).

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.

## 5. Reliability, 77 out of 100, up to 4.6 more on the total

Why it scored 77: Read with the hosted lines and scored on the REST API at api.shipbob.com. Statuspage at status.shipbob.com with three components and 90-day uptime bars (20). The history shows no incident from August to October 2026 and the incident feed is empty. The page says it reports major outages of the website or dashboard, has no API component and has posted no incident since it was created in July 2024, so the clean record says little about the API. We scored it as minor only instead of clean, a departure from the checklist (20 of 30). 150 requests a minute, sliding window, per user and application (15). A 429 carries `x-retry-after`, the errors page recommends exponential backoff, and a duplicate `reference_id` returns 422, which makes a retried create safe. No idempotency key (12 of 15). The terms publish fulfilment turnaround SLAs with 14 exclusions. No uptime SLA for the API was found (0). The dated API versions are generally available (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.

## 6. Schema & documentation, 85 out of 100, up to 2.4 more on the total

Why it scored 85: OpenAPI 3.0 spec for each version at marketplaceapi.shipbob.com, 89 operations in 2026-07. The `openapi.json` link in the docs index returns an HTML page, not the spec (25). llms.txt per version and a Markdown copy of each page (10). 88 of 89 operations have a description, and some say when to use them, such as the inventory level call for current stock questions. Few say when not to (14 of 20). All 199 parameters have a schema, with 46 enums and required fields marked. Sort order and shipping method are free strings, and many filters are comma-separated lists (10 of 15). 504 examples. 401 and 403 are documented on 64 operations, 400 on 58 and 422 on 18, 429 on none, and error bodies differ by domain, with RFC 7807 problem details in some and an `errors` array in others (11 of 15). Date-based versions, an upgrade guide per version and dated 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. Transparency & trust, 77 out of 100, up to 2 more on the total

Made of editorial 69, provenance 85.

Why it scored 77: Closed service. The Terms of Service, updated 22 May 2026, name ShipBob, Inc. and Illinois law. The tutorials repository has no licence file (15 of 30). A privacy policy dated 29 March 2024, which says it doesn't apply where a commercial contract governs, and a DPA dated April 2026 under which ShipBob deletes or returns personal data at the end of the service if the merchant asks. No retention period is stated in days, and the terms grant ShipBob a perpetual right to use merchant content for product improvement (17 of 30). A written version policy with 24 months of support for each version, end dates in a table, and the phased shutdown of 1.0 published with dates (20 of 20). A public list of about 30 subprocessors with purpose and location, all in the United States, with no date on the page (17 of 20).

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 7 of the 7 things a reader expects, and has 2 clauses that cost points (6 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)

## 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 hosted MCP server's tool definitions, input schemas and annotations, which need a ShipBob sign-in. The count of 73 is from the docs
- unchecked: the turnaround times and SLA article on support.shipbob.com that the terms link to. We read the SLA clause in the terms only, and found no API uptime commitment there
- unchecked: whether signup asks for a real card before a production token is issued. The docs say accounts are free until inventory arrives
- unchecked: the SOC 2 and ISO 27001 reports and their dates, which the Trust Center gives on request
- unchecked: the Claude connector directory entry for ShipBob MCP that the troubleshooting page describes
- Whether the API has had outages in the last 90 days. The status page has no API component and no incident posted
- Whether an official SDK exists. None is mentioned in the docs or found under the ShipBob GitHub organisation
- Unit prices for fulfilment. None are public, so the listing has no price table
- The day in July 2026 on which PKCE was added to the OAuth flow, and when the MCP server grew from 27 to 73 tools

## Weaknesses

- No public price. Receiving, storage and pick, pack and ship fees come only in a quote from sales
- The status page lists the merchant dashboard and two warehouse systems, with no component for the API and no incident posted
- Personal Access Tokens don't expire and carry every scope, with no read-only option
- No official SDK was found, and the MCP server is not in the official MCP registry
- No idempotency key. A retried create is caught only by the unique `reference_id`, which returns 422
- No security.txt, disclosure policy or bug bounty was found, and no API uptime SLA is published

## 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.

- Call `GET /2026-07/channel` first and send the ID of the channel with `_write` scopes in the `shipbob_channel_id` header on every write
- Build against `https://sandbox-api.shipbob.com` with a sandbox account. Sandbox and production accounts, tokens and data are separate
- Set a stable `reference_id` on each order, product and return. A duplicate returns 422, which is the only guard against a double create
- Stay under 150 requests a minute per user and application, and wait the seconds given in `x-retry-after` after a 429
- Over MCP, writes work only on records in the channel created at consent. A 403 or 404 on a cancel usually means the record belongs to another channel

## 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.