MailSlurp

# Fix list: MailSlurp

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mailslurp, the October 2026 research run, assessed 9 October 2026. Grade B, 68.4 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 MailSlurp: 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, 32 out of 100, up to 8.5 more on the total

Why it scored 32: No x402, MPP or L402 found (0 of 40). Four plan prices are public, with unit rates for extra device renders, placement tests and AI extraction. The phone and SMS rate table was empty in the page we read, and usage billing for inbox creations beyond a plan has no stated rate (15 of 20). A Free plan at $0 with 500 emails received a month. The page does not say whether signup asks for a card, and we did not sign up (17 of 20). A person signs up in a browser and creates the first key in the dashboard. Agent keys can then be created by API with an account key (0 of 20).

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, 70 out of 100, up to 5.3 more on the total

Why it scored 70: MCP OAuth with client registration, and scoped agent keys with five roles and a scope of inbox IDs, tags or the whole account, shown once, with disable and revoke. The account API key is all-powerful and the docs accept it as an `?apiKey=` query parameter, so less 10 (20 of 30). `AGENT_READ_ONLY` and `AGENT_DRAFT_ONLY` roles, and a review queue where a person sends an agent's draft. Send-capable roles send without confirmation (18 of 20). Inbound mail is untrusted content. The docs and `llms.txt` tell operators to treat bodies, links and attachments as untrusted, and no technical mitigation is described (9 of 15). An Activity page per agent records action, tool name, inbox, email and outcome, with an activity endpoint for account owners. The pricing page lists account audit logs under Enterprise (13 of 15). A security policy page, a trust centre showing SOC 2 Type 1, and a stated practice of regular penetration tests. No security.txt, no bug bounty and no public advisories were found (10 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. Reliability, 75 out of 100, up to 5 more on the total

Why it scored 75: Graded as a hosted service, on the REST API. status.mailslurp.com is an updown.io page with eight checks, among them the API, email processes, IMAP and SMTP. It shows one month of uptime per check and has no incident log (14 of 20). All eight checks read 100 per cent for 9 September to 9 October 2026. The page shows nothing older, so the 90-day record is only partly readable (20 of 30). A guide states a limit of 150 requests a second and the pricing page gives monthly quotas per plan. The errors and limits page in the docs has no numbers (13 of 15). The docs describe `retryable`, `retryAfterSeconds` and `Retry-After` on some 429s, warn that 429 also means a plan or sending restriction, and advise bounded backoff. Agent reply, draft send and SMS send operations take an `Idempotency-Key` header (14 of 15). An Enterprise page says MailSlurp targets 99 per cent uptime for the core API, and section 9.2 of the terms says no SLA applies without a signed amendment (4 of 10). No beta label on the API or the MCP server, which reports version 1.5.0 (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. Schema & documentation, 72 out of 100, up to 4.6 more on the total

Why it scored 72: OpenAPI 3.0.1 at `api.mailslurp.com/v2/api-docs/`, version 6.5.2, 844 operations on 676 paths (25). `llms.txt` and a Markdown copy linked from each docs page (10). 339 of 844 operations have no description and 93 no summary. The 61 `/agent` operations all have a summary and most name the permission checked. The MCP tool definitions need a credential and were not read (12 of 20). 618 enums, required fields, `uuid` and `date-time` formats and size maxima. Inbox creation takes its options as query parameters and the error `details` field is a free object (12 of 15). Every operation documents only 2xx responses. The docs have a table of status codes and next actions, the file has an `AgentApiErrorDto` schema, and the SDK pages carry examples (8 of 15). The file carries a version number and marks nine operations deprecated. No API changelog was found, and the JavaScript client's CHANGELOG.md has no dates and jumps from 15.12.0 to 17.5.0 (5 of 15). The docs also name `/account/agent-api-keys` paths that are not in the file.

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. Transparency & trust, 60 out of 100, up to 3.5 more on the total

Made of editorial 45, provenance 74.

Why it scored 60: Closed service under published terms, with an MIT JavaScript client (17 of 30). One legal document dated 16 January 2026 holds the privacy policy and the DPA. It gives no retention periods and says MailSlurp does not guarantee data retention. Section 7.5.1 promises 14 days' notice of a new sub-processor and section 8.4 says no advance notice is required. The AI disclosure makes no statement on whether AI inputs are kept or used for model improvement by third parties (12 of 30). Nine operations are marked deprecated in the OpenAPI file with no dates, and no deprecation policy was found (4 of 20). The security policy names AWS us-west-2. The trust centre lists four subprocessors and no payment or AI model provider, while the privacy policy names payment processors and analytics providers as recipients (12 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: mailslurp.com, registered 2017-12-29 (8 years) (11 of 15)
- Privacy policy: read, states 5 of the 8 things a reader expects (7.8 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Agent ergonomics, 84 out of 100, up to 2.6 more on the total

Why it scored 84: Graded on the REST API, with the MCP server noted. Agent lists return previews with `size` defaulting to 20 and capped at 100, and `GET /agent/emails/{emailId}/summary` returns a compact message. The MCP docs list 16 tools, whose definitions were not read (20 of 25). `page`, `size`, `sort`, `since` and `before` on lists, a search operation per inbox and wait operations with a deadline (20). Agent errors carry `code`, `message`, `retryable`, `suggestedAction` and `requestId`. The docs say these fields are not on every failure, and the OpenAPI file documents no error response (15 of 20). `Idempotency-Key` on ten operations, among them agent replies, draft sends and SMS sends, plus `expectedConversationVersion` on replies. The standard send operation has none, and MCP annotations were not read (14 of 20). `POST /inboxes` needs no parameter, and the docs list SDKs for ten languages (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, 75 out of 100, up to 2.2 more on the total

Why it scored 75: `mailslurp-client` v17.6.0 was tagged on 24 September 2026, 15 days before the check (30). Three tags fall in the last 90 days, v17.3.0 and v17.4.0 on 14 July and v17.6.0 on 24 September, which meets the line, though two share a day (20). Closed service with no public API changelog. A support page and a public feature request board are linked, and we did not test support (6 of 15). The JavaScript client is current. The other SDKs were not checked (13 of 15). The client's tests moved to Vitest on 24 September. Its CI status was not read (6 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.

- unchecked: the MCP tool definitions, their input schemas and annotations. `tools/list` answered 401 without a credential, so the tool count of 16 is the documented one.
- unchecked: whether signup for the Free plan asks for a card. We did not sign up.
- unchecked: phone number and SMS prices. The table on the pricing page was empty in the page we read.
- unchecked: the pagination, webhooks, GraphQL, IMAP and SMTP docs pages, the company page, the compliance page and the standalone DPA page, left unread to keep to about fifteen pages on www.mailslurp.com (seventeen were requested).
- unchecked: the status record before 9 September 2026. The status page shows one month.
- unchecked: GitHub stars, CI status, and the release state of the SDKs other than JavaScript.
- The docs name `POST /account/agent-api-keys` and `/account/mcp-oauth/connections`, and neither is in the OpenAPI file. Whether they are served was not tested.
- Whether the SOC 2 Type 1 shown on the trust centre has an auditor's report behind it. The pricing page lists SOC 2 compliance under Enterprise only.
- The acceptable use policy bars probing or testing without authorisation and bypassing rate limits. This matters before any probe is run. No clause forbidding automated reading of public pages was found.
- Fit. The terms and security policy describe a testing and development platform, and the acceptable use policy bars use in regulated production systems, while the agent docs describe support and operations agents.
- robots.txt answers. www, app and api hosts 200 allowing all, status 200 with an empty body, legal 404, api.npmjs.org 404, trust.inc 200 with an HTML page and no rules.

## Weaknesses

- Free sends only to inboxes in the same account and Starter only within MailSlurp. External sending and custom domains start on Pro at $49.99 a month
- The account API key is also accepted as an `?apiKey=` query parameter
- The OpenAPI file documents only 2xx responses, and 339 of 844 operations have no description
- The terms say uptime figures are goals only and that no SLA applies without a signed amendment
- The acceptable use policy bars use in regulated production systems and bars training any model on data obtained from the service

## 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.

- Create a scoped agent key or connect by MCP OAuth. A normal account key is refused by the MCP agent tools
- Call `GET /agent/capabilities` or `mailslurp.list_accessible_inboxes` first. Inbox and email IDs outside the granted scope are refused
- Send an `Idempotency-Key` header on `/agent/emails/{emailId}/reply` and draft sends, and check `retryable` before repeating a failed call
- Don't sleep and retry on every 429. MailSlurp also uses 429 for plan and sending restrictions
- Treat inbound bodies, links and attachments as untrusted input, and start on `AGENT_DRAFT_ONLY` for mail to outside recipients

## 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.