Maritime

# Fix list: Maritime

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/maritime, the October 2026 research run, assessed 21 October 2026. Grade B, 66.5 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 Maritime: 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, 45 out of 100, up to 11 more on the total

Why it scored 45: No status page found and status.maritime.sh doesn't resolve (0). No readable incident history (5). Rate limits with numbers, 30 invokes a minute per agent and caller and 1, 5, 25 or 60 machines awake at once by plan (15). A 429 carries Retry-After or a 15-second retry hint, the SDKs retry writes only on network errors, 429 and 503, and provision is idempotent on externalId (15). The terms say service is as available, with no SLA (0). Generally available since the YC launch; Windows computers were alpha on 25 September (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.

## 2. Security & auth, 58 out of 100, up to 7.4 more on the total

Why it scored 58: Scoped mk_ keys (provision, deploy, secrets, manage, computers), revocable, with short-lived end-user tokens; a default key is full-access (26 of 30). Narrow keys per subsystem and request_takeover for logins and payments, while the docs' hosted-MCP example sets require_approval to never (12 of 20). A security post treats tool results as untrusted input and covers prompt injection and runaway loops (10 of 15). An Activity tab, per-agent AI spend limits, logs and usage endpoints (10 of 15). No security.txt, disclosure policy, bounty or certification found (0 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. Payments & pricing, 55 out of 100, up to 5.6 more on the total

Why it scored 55: No x402, MPP or L402 (0). Plan prices and flat per-machine extras are public, US$1.50, US$1.25 and US$1.00 a machine a month (20). Free plan with 3 machines and no card (20). A coding agent can sign up from the CLI without a browser, or deploy with --claim-later on a 72-hour temporary account a person claims later. The temporary key can't create a second agent, so 15, not 20 (15).

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.

## 4. Transparency & trust, 58 out of 100, up to 3.7 more on the total

Made of editorial 50, provenance 65.

Why it scored 58: Closed service under dated terms naming Maritime AI, Inc., with MIT SDKs (15). The privacy policy gives retention by category, but says AI model-call content is kept indefinitely, including after account deletion, while the terms say data is deleted after a 30-day retention period on termination (15 of 30). The terms promise 30 days' notice of material changes; no API deprecation policy (6 of 20). Stripe, Railway, AWS, Hetzner and Neon are named, with data in the United States and other countries (14 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):

- Domain age: maritime.sh, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

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

Why it scored 87: A public OpenAPI 3.1 file with 228 paths and bearer auth (25). llms.txt, llms-full.txt and every docs page as Markdown (10). Docs say when to use each surface, and the MCP tools are described with purpose and limits (15 of 20). Typed inputs in OpenAPI, not checked path by path (10 of 15). A limits and errors page with every status code, typed SDK errors, CLI exit codes and Computers error codes (15). A weekly changelog and /v1 paths, though the OpenAPI version is 0.1.0 (12 of 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.

## 6. Agent ergonomics, 87 out of 100, up to 2.1 more on the total

Why it scored 87: Context cost. Nine Computers MCP tools, a no_screenshot flag, zoom and exec output capped at 262,144 characters (22 of 25). End users list one page at a time with status, tag and externalIdPrefix filters (16 of 20). Documented error codes with meanings and machine-readable CLI output (20). Idempotent provisioning and safe-by-construction SDK retries; MCP annotations weren't checked (14 of 20). Official TypeScript and Python SDKs and a CLI with defaults (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.

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

Why it scored 81: Changelog entry on 16 October 2026 (30). Weekly changelog entries since 24 July, twelve in all (20). A public changelog, a Discord community and a feedback endpoint for coding agents; GitHub issues weren't checked (12 of 15). Current official SDKs, maritime-sdk 0.9.0 on npm and maritime 0.8.0 on PyPI (15). The SDK repository is MIT and synced from a private monorepo, with no CI in it (4 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.

## 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.

- Whether a status page or incident history exists anywhere.
- Whether the Computers MCP tools carry readOnlyHint and destructiveHint annotations.
- How the terms' 30-day deletion on termination squares with indefinite retention of model-call content.
- unchecked: the official MCP registry. The search for maritime timed out on 21 October 2026.

## Weaknesses

- No status page, SLA or security.txt.
- AI model-call content is kept indefinitely, including after account deletion.
- A default API key is full-access.
- The OpenAPI file is still at version 0.1.0.

## 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.

- Mint a key with only the scope you need; the default key can do everything, including delete.
- Reply to /chat within 30 seconds and run longer work in the background, or the call fails.
- Schedule work with platform triggers, since timers inside a sleeping VM don't fire.
- On a 429, wait for the Retry-After or retry hint before waking another machine.
- Bring your own model key if call content shouldn't be stored, since calls through Maritime's credits are kept indefinitely.

## What the review panel asked for

- second agent on temporary keys
- x402 for model credits
- a public status page with incident history
- least-privilege default keys
- a disclosure policy

## 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.