Mailjet API + MCP by Mailjet (Sinch)

# Fix list: Mailjet API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mailjet, the October 2026 research run, assessed 1 October 2026. Grade C, 59.5 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 Mailjet API + MCP: 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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Plan prices are public, but the price per extra 1,000 emails sits behind a help-centre link rather than on the pricing page (10). Free plan of 6,000 emails a month, 200 a day, with no card (20). Browser signup, no autonomous route (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, 52 out of 100, up to 8.4 more on the total

Why it scored 52: Email API calls use Basic auth with a public key and a secret. Sub-accounts get their own keys, and the Content API also takes Bearer tokens with permissions and a 365-day default expiry (22). The MCP server can only read, by construction. We found no send-only or read-only key for the Email API (10). The MCP returns contacts, lists and statistics, and inbound mail goes from the Parse API to your webhook rather than through the tools (10). No audit log or per-key activity view found (0). ISO 27001, SOC 2, HIPAA and CSA badges on the security page. No bug bounty, disclosure policy or security.txt 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. Reliability, 62 out of 100, up to 7.6 more on the total

Why it scored 62: Statuspage at mailjet.statuspage.io with history back to 2023 (20). The only entry since 1 July is a planned hour of maintenance on 23 September, during which logins and API and SMTP sends were unavailable and submitted mail waited in the queue. We count that as minor (20). The rate-limit page says transactional endpoints have a high limit and others a 'much lower' one, with no numbers (0). A 429 on excess and advice to wait and retry, but no Retry-After header and no idempotency key for sends. SandboxMode validates a send without delivering (7). Enterprise plans list a 'Service Level Agreement' with no published terms (5). GA (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, 53 out of 100, up to 7.6 more on the total

Why it scored 53: The MCP server registers one tool for each of the 117 GET paths in its bundled spec, with no toolsets (5). Limit, Offset, Sort and countOnly on list resources (15). Documented status codes and error codes with messages (14). Every MCP tool is a GET, so nothing it does can change the account, but no tool carries readOnlyHint, and the Send API has no idempotency key (6). Official SDKs for Node, Python and other languages, one POST /v3.1/send call carries a Messages array, and the MCP needs the key and secret joined as `key:secret` (13).

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. Schema & documentation, 76 out of 100, up to 3.9 more on the total

Why it scored 76: Published OpenAPI files, and the MCP server bundles a 528 KB copy (25). llms.txt with about 120 links and Markdown pages (10). MCP tool descriptions are the operation summary only, and the reference describes each resource without saying when not to use it (8). Typed from OpenAPI, with Limit, Offset, Sort and countOnly parameters across GET resources (11). Status-code and error-code pages, and examples per endpoint (12). Send API v3 and v3.1 are versioned, and the releases page has dated entries, but they're product launches rather than an API 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.

## 6. Transparency & trust, 73 out of 100, up to 2.4 more on the total

Made of editorial 55, provenance 90.

Why it scored 73: Closed service with published terms that name Mailjet SAS, Mailjet GmbH or Mailgun Technologies, Inc. depending on the customer, and an Apache-2.0 MCP server (20). Data stored on Google Cloud in Frankfurt and Saint-Ghislain, a Sinch DPA and a named DPO, but no retention periods stated (18). No API deprecation notices or policy found (5). Data locations are stated. We found no subprocessor list (12).

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):

- security.txt: not found (0 of 10)

## 7. Maintenance & community, 79 out of 100, up to 1.8 more on the total

Why it scored 79: mailjet-apiv3-python v1.9.0 on 14 September and a release entry on 3 September (30). Python 1.8.0 (17 August) and 1.9.0, node-mailjet v7.1.0 (14 August) and release entries on 27 July and 3 September (20). The MCP repository merges pull requests and its README asks users to file an issue if npm and GitHub diverge. We couldn't see issue reply times (8). Node and Python SDKs released in the last 50 days (15). CI runs the tests, but npm has MCP 1.1.0 while the git tags stop at v1.1.0-beta.1 (6).

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.

- Price per extra 1,000 emails, which the pricing page links to but doesn't show
- Numeric rate limits for the Send API and other endpoints
- Whether shorter incidents are posted to the status page, whose feed has few entries since 2023
- Release date of MCP 1.1.0 on npm, since git tags stop at v1.1.0-beta.1

## Weaknesses

- The MCP server registers 117 GET-only tools and can't send
- No numeric rate limits published
- Price per extra 1,000 emails isn't on the pricing page
- No bug bounty, disclosure policy or security.txt found
- npm has MCP 1.1.0 while the git tags stop at a beta

## 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.

- Set `SandboxMode` to true on the first sends to check payloads without delivering
- Send with POST /v3.1/send and a `Messages` array, many messages per call
- Use the MCP for statistics and contact lookups only, since it can't send
- Pass `MAILJET_API_KEY` as `key:secret`. The server checks it at startup and exits if it's wrong
- On 429, wait and retry. Non-transactional endpoints have much lower limits than send

## What the review panel asked for

- Clarify sandbox verification
- Publish numeric limits
- Add idempotency keys

## 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.