Easyship

# Fix list: Easyship

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/easyship, the October 2026 research run, assessed 7 October 2026. Grade B, 68.8 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 Easyship: 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, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Plan prices and per-call prices for the metered endpoints are public in the data file the plans page loads, for example US$0.01 a rates call on Free and US$29 a month for Plus. Label prices depend on the courier and come back from the rates call (20). The Free plan needs no card and covers 50 shipments a month in the US, and paid plans have a 14-day trial (20). A person signs up in a browser and creates the token in the dashboard, or approves OAuth (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, 61 out of 100, up to 6.8 more on the total

Why it scored 61: API tokens are created in the dashboard with per-resource scopes such as `public.shipment:read` and `public.label:write` on v2024-09, are revocable, and are separate for sandbox and production. The MCP server also publishes OAuth metadata with PKCE S256 and dynamic client registration. No token expiry was found (26). Read-only scopes make a read-only agent possible. Confirmation before delete and cancel exists only as a rule file in the plugin repository, not in the server (14). The MCP server strips tax identifiers from every response and withholds contact details and document links by default. No guidance on untrusted text in tracking or address fields was found (7). Transaction records and a request_id on errors are available. No API call log for the operator was found (4). security.txt is present but expired on 5 October 2025. It points to a disclosure policy at vdp.easyship.com, which needs JavaScript and went unread. The developers page claims SOC certification with no report or trust page found (10).

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, 73 out of 100, up to 4.4 more on the total

Why it scored 73: The MCP server loads 25 tools with no toolsets. List tools return allow-listed summaries, and documents and contact details come back only when asked for (18). List endpoints take page and per_page (default 20) and filters by state, date, country and order number (20). Errors carry a code, type, details array, documentation links and a request_id (18). No idempotency keys, so a retried label purchase isn't protected. All 25 MCP tools set readOnlyHint, destructiveHint and openWorldHint (10). create_shipment picks a courier when none is given and get_rates needs six fields. No official SDK was found among the 15 public repositories in Easyship's GitHub organisation, though the developers page mentions SDKs (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.

## 4. Reliability, 80 out of 100, up to 4 more on the total

Why it scored 80: Graded on the public API v2024-09, which the hosted MCP server calls. Statuspage at status.easyship.com with nine Easyship components, among them Core API, Open API and Rates API (20). The incident feed holds 42 entries back to 2020 and none in the last 90 days. The latest are a Cloudflare-related website outage of 11 minutes on 5 December 2025 and a critical Cloudflare incident of 6 hours 43 minutes on 18 November 2025 (30). Limits are published as 60 requests a minute and 10 a second, 6 a minute in sandbox (15). The 429 `too_many_requests` code is documented with the advice to wait for the next window. No Retry-After header, backoff guidance or idempotency key was found in the docs or the spec (5). The developers page claims both 99.9% and 99.99% uptime, the US terms disclaim uninterrupted access, and no SLA was found (0). Version 2024-09 is described as the latest stable version. The MCP package is classified beta on PyPI (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.

## 5. Maintenance & community, 56 out of 100, up to 3.9 more on the total

Why it scored 56: easyship-mcp 0.6.5 was published on 21 August 2026, 47 days ago. The API changelog's last entry is 30 October 2025 (20). Three releases fall in the last 90 days, 0.6.3 to 0.6.5, all on 21 August, so half credit (10). Closed service with a support desk and a bug report form. The plugin repository has seven commits, the last on 23 June 2026, and the API changelog has been silent for 11 months (6). Listed in the official MCP registry as com.easyship/mcp, a domain-verified namespace, with 0.6.5 as latest (15). The package pins fastmcp below 4 with a uv.lock and has version-check and deploy workflows. No tests ship in the source package (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, 71 out of 100, up to 2.5 more on the total

Made of editorial 51, provenance 91.

Why it scored 71: Closed service under country-specific terms, the US version updated 28 July 2026 and naming Easyship Inc. The MCP server and plugin are MIT (17). The privacy policy of 28 July 2026 gives retention periods (account and shipment data for their lifetime plus seven years) and bars providers from training general-purpose AI on personal information. The DPA of 28 March 2025 says personal data is deleted on deactivation unless law requires otherwise, which sits uneasily with seven years (18). Deprecated endpoints are marked and migration guides exist, and the US terms promise 30 days' notice of material changes. No API deprecation policy with dates was found (8). The sub-processor list the DPA points to is dated 15 October 2020, names only analytics, advertising and CRM tools and cites Privacy Shield. The privacy policy names the United States and Singapore as processing locations (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 7 of the 7 things a reader expects, and has 2 clauses that cost points (6 of 10)
- security.txt: published but past its Expires date (5 of 10)

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

Why it scored 87: Every reference page has a Markdown twin with its OpenAPI 3.0.3 definition, and the full v2024-09 spec (132 operations on 98 paths) ships in the easyship-mcp source package. No single spec URL was found on the docs site. MCP inputs are typed with Pydantic (25). llms.txt at developers.easyship.com lists 240 lines of Markdown pages (10). MCP descriptions state what to collect before calling, when to buy a label or only draft a shipment, and which tool to use for detail. Not every tool says when not to use it (17). The spec has 177 enum declarations and required fields. In the MCP, incoterms, currency and item category are free strings (12). Twelve error codes are documented with HTTP status and a worked example, and endpoints list 402 and 422 responses (13). Versions are dated in the path (2023-01, 2024-09) with migration guides. The changelog's last entry is 30 October 2025, and the MCP server has no changelog (10).

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.

## 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 vulnerability disclosure policy at vdp.easyship.com/p/policy, which renders only with JavaScript
- unchecked: the authentication guide at developers.easyship.com/docs/authentication, whose Markdown twin didn't load
- The static markup of the plans page shows other per-call figures (US$0.003 to US$0.005 overage) than the data file the page loads (US$0.006 to US$0.01 for rates). We used the data file's US rows
- Whether the 30 October 2025 sandbox domain change, marked breaking in the changelog, was announced in advance. No deduction was taken
- Whether 429 responses carry a Retry-After header in practice
- What the SOC certification claimed on the developers page covers. No report, type or trust page was found
- Whether an SLA exists on Enterprise contracts
- When the public API first launched. firstReleased is left empty
- GitHub star count for the plugin repository read 0 through the API on 7 October 2026

## Weaknesses

- No idempotency keys in the 132-operation spec, and no Retry-After or backoff guidance for 429
- The MCP server has no test mode, so a label bought through it is charged
- API changelog's last entry is 30 October 2025, and no deprecation policy was found
- security.txt expired on 5 October 2025, and the sub-processor list is dated 15 October 2020
- No official SDKs found, and the published limit is 60 requests a minute

## 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 a sand_ token against https://public-api-sandbox.easyship.com for API tests. Production rejects sandbox tokens, and sandbox allows 6 requests a minute
- The MCP server calls production only. Create the shipment without buy_label first, then call create_label once the user confirms the courier and price
- Don't retry a timed-out label purchase blindly. There's no idempotency key, so read the shipment's label_state first
- Give every item a category or an hs_code. The API rejects shipments and rates requests that have neither
- Stay under 60 requests a minute and 10 a second, and wait for the next window on 429

## 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.