SMTP2GO API + MCP by SMTP2GO

# Fix list: SMTP2GO API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/smtp2go, the October 2026 research run, assessed 1 October 2026. Grade D, 53.2 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 SMTP2GO 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. Reliability, 47 out of 100, up to 10.6 more on the total

Why it scored 47: Statuspage at smtp2gostatus.com with history (20). Since July, mail held as 'processed' for about 11 hours on 25 to 26 July and 3 hours 20 minutes on 27 August, connectivity problems for about 6.5 hours on 25 September, 2 hours of inbound timeouts on 29 September, AU delivery delays over about 7.5 hours on 30 September, and connection issues still under investigation on 1 October with email sending shown as degraded. Several majors (0). Numbers for /activity/search (60 a minute), new paid accounts (1,000 a day until reviewed) and free accounts (200 a day, 25 an hour without a verified domain), with optional per-key send rates, but no general API limit (12). 429 plus an IP timeout of at least a minute, with advice to pause and slow down. No Retry-After and no idempotency key (5). No SLA found (0). 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.

## 2. 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 overage ($1 and $0.85 per 1,000) published without login (20). Free plan of 1,000 emails a month, 200 a day, with no card (20). Browser signup and a review of new paid accounts, 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.

## 3. Security & auth, 60 out of 100, up to 7 more on the total

Why it scored 60: API keys with per-endpoint permissions and their own send rate, IP allow lists for API and SMTP separately since 30 July, and keys masked in API responses since 22 June. The key can also travel in the JSON body, which the official Node SDK does by default (24). The MCP docs ask for a narrowly scoped key and list the three permissions a sender needs (14). No inbound mail, so the tools return only account data (10). Activity reporting for 30 days on paid plans, no per-key audit log found (6). ISO 27001 compliance claimed in the privacy policy. No security.txt, disclosure policy or security page found, and /security returns 404 (6).

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.

## 4. Schema & documentation, 59 out of 100, up to 6.7 more on the total

Why it scored 59: No public OpenAPI file found, and the hosted MCP sends every call through one generic execute-request tool rather than a typed tool per endpoint (5). llms.txt with about 100 links and Markdown pages (10). Reference pages explain each endpoint, and the MCP's four docs tools let a model look one up before calling it (12). Request bodies through execute-request aren't typed per endpoint (5). A response-codes page and examples per endpoint (12). Dated changelog that flags breaking changes, and v3 in the path (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.

## 5. Agent ergonomics, 66 out of 100, up to 5.5 more on the total

Why it scored 66: Five tools, four of them read-only docs lookups (25). We didn't check pagination or output limits on /activity/search beyond its 60-a-minute limit (8). Documented response codes with messages (14). The docs tools only read. execute-request can send or delete with nothing marking it so that we found, and there's no idempotency key (6). Node and Python SDKs, and a send needs only sender, to, subject and a body (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.

## 6. Maintenance & community, 53 out of 100, up to 4.1 more on the total

Why it scored 53: Changelog entry on 7 September (Bearer auth), 24 days before this check (30). Only 7 September and 30 July fall inside 90 days, and smtp2go-nodejs 1.0.0 shipped on 5 June, so fewer than three (0). Public changelog and ticket, chat and phone support (10). Node SDK at 1.0.0 since June and a Python package, both little used (10). No CI configuration in the Node SDK repository (3).

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.

## 7. Transparency & trust, 72 out of 100, up to 2.5 more on the total

Made of editorial 54, provenance 90.

Why it scored 72: Closed service with published terms and an MIT Node SDK (20). The privacy policy, last updated 23 July 2023, says headers and a sample of one email in a thousand are kept 35 days and that EEA users' personal data stays in the EEA. DPA on request (18). Breaking changes are flagged in the changelog with no notice period (8). Data centres in the US, Europe and Australia, no subprocessor list (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):

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

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- 2026-06-11. The changelog marks a request-body cap (1 MB for non-email calls, 50 MB for email) as breaking and gives no notice period, and stricter API key permission rules shipped the same way on 2026-05-29. -3 (https://developers.smtp2go.com/reference/changelog)

## 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 the 11 June and 29 May breaking changes were announced to customers before they shipped
- Pagination and output limits on /activity/search
- Whether failed sends count against the plan
- A subprocessor list, which the privacy policy doesn't give

## Weaknesses

- Several multi-hour delivery and connectivity incidents since July, and degraded sending on 1 October
- No public OpenAPI file and an untyped execute-request tool
- No inbound email
- The official Node SDK sends the API key in the JSON body
- No security.txt, disclosure policy or security page found

## 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.

- Give the MCP a key limited to /email/send and the view endpoints it needs, since execute-request can call anything the key allows
- Send the key in the `X-Smtp2go-Api-Key` header or as Bearer, not in the JSON body, so it stays out of request logs
- Verify a sender domain first. Free accounts without one are held to 25 emails an hour
- On 429, pause until calls return 200 again. Repeated errors time out your IP for at least a minute
- Check smtp2gostatus.com before blaming your payload for mail stuck as 'processed'

## What the review panel asked for

- Document key issuing
- Publish a general limit
- Publish an SLA

## 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.