Mailgun API + MCP by Mailgun (Sinch)

# Fix list: Mailgun API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mailgun, the October 2026 research run, assessed 1 October 2026. Grade B, 66.3 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 Mailgun 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, 57 out of 100, up to 8.6 more on the total

Why it scored 57: Statuspage at status.mailgun.com with dated history (20). Twelve incidents between 10 July and 30 September. The worst were US validation API errors with the control panel down for 93 minutes on 13 July, a US event-log backlog of about 7 hours on 31 August, and EU sending outages of 38 minutes on 27 August and 17 minutes on 4 September. None was an hour of the core send API down, but we count the validation outage as one major (10). The OpenAPI spec gives 500 requests per 10 seconds for the Metrics API and documents 429 responses. No general send limit is published (7). No Retry-After or backoff guidance and no idempotency key on POST /messages that we found (5). Pricing lists a 'Guaranteed Uptime SLA' 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.

## 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 per-1,000 overage ($1.80, $1.30, $1.10) published without login (20). Free plan of 100 emails a day with no card (20). A person signs up in a browser and verifies a domain, so 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. Agent ergonomics, 60 out of 100, up to 6.5 more on the total

Why it scored 60: 74 tools register by default (70 send endpoints, one each for `validate`, `optimize` and `inspect`, and a metrics summary), so 5. `--tags` or `MAILGUN_MCP_TAGS` filters by product, but nearly everything is tagged send, so we add back 3 (8). Logs and analytics take limits, pagination and filters (18). The server turns API errors into messages that name the endpoint and the fix, and a 403 points at the billing page (16). No readOnlyHint or destructiveHint on any tool and no idempotency key for sends. `o:testmode` lets an agent check a send without delivery (4). Official Node and Python SDKs, and a send needs from, to, subject and a body (14).

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. Security & auth, 74 out of 100, up to 4.6 more on the total

Why it scored 74: HTTP Basic auth with a key. Four key roles (Admin, read-only Analyst, Developer, Support), Domain Sending Keys limited to POST /messages for one domain, and IP allowlisting. Rotation is advised but keys don't expire (28). The Analyst role is read-only, sending keys cover the least-privilege case, and the MCP server exposes no delete operations. Confirmation is left to the client (15). The MCP can fetch stored messages, so inbound mail can reach the model. The README's prompt-injection section asks users to review tool calls and goes no further (6). Logs API with 1 to 30 days of retention by plan, and Mailgun says security logs are kept 365 days (10). SOC 2 Type II, ISO 27001 and a third-party bug bounty per the security page, no security.txt (15).

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.

## 5. Schema & documentation, 83 out of 100, up to 2.8 more on the total

Why it scored 83: OpenAPI 3.1 for `send`, `validate`, `optimize` and `inspect`, and every MCP tool takes a Zod schema built from it (25). llms.txt with about 145 links and Markdown pages (10). MCP tool descriptions are the OpenAPI operation summary, one line each, with nothing on when to use or avoid a tool (8). Inputs are typed from the spec, though the README says some edge-case parameters fall back to permissive validation (12). The spec carries request and error examples, and the server rewrites 400, 401, 403 and 404 into guidance (13). Dated release notes and a semver CHANGELOG for the MCP server (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. Transparency & trust, 70 out of 100, up to 2.6 more on the total

Made of editorial 64, provenance 75.

Why it scored 70: Closed service with published terms that name Sinch Email and the entity on the service order rather than one company. The MCP server is Apache-2.0 (18). Log retention by plan (1, 5 or 30 days) is on the pricing page, security logs 365 days, and a Sinch DPA is linked from the security page (22). Release notes date changes such as the May 2025 SMTP login change, and the MCP CHANGELOG flags its 2.0.0 tool renames, but we found no deprecation policy (12). Hosted on Google Cloud in US and EU regions. We didn't find a 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):

- Endpoint on the vendor's domain: api.mailgun.net is not on mailgun.com (0 of 15)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 87 out of 100, up to 1.1 more on the total

Why it scored 87: Release notes on 22, 15, 8 and 1 September, mailgun-python 1.9.1 on 21 September and MCP 2.1.3 on 16 September (30). Well over three dated releases in 90 days (20). The MCP repository merges pull requests and tags each release. We couldn't see open issues or reply times from git (12). mailgun.js 14.0.1 (4 September) and mailgun-python are current (15). MCP CI runs tests on Node 20, 22 and 24 plus lint, and npm releases publish from a workflow (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.

- Open issue count and reply times on the MCP repository, which git doesn't show
- Terms behind the 'Guaranteed Uptime SLA' on the pricing page
- Whether rejected sends count against the plan
- The repository's server.json names com.mailgun/mailgun-mcp-server, but the official MCP registry returned no Mailgun entry under that name

## Weaknesses

- 74 MCP tools load by default, each a one-line summary, with no readOnlyHint or destructiveHint
- 12 status incidents since 10 July, including 93 minutes of US validation API errors
- No general API rate limit published and no idempotency key for sends
- Free plan keeps logs for 1 day and allows 1 inbound route
- No security.txt

## 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 an agent that only sends a Domain Sending Key, which can only POST /messages for one domain
- Start the MCP with `--tags validate,inspect` when you don't need the 70 send-tagged tools
- Set `MAILGUN_API_REGION=eu` for EU accounts, which live on api.eu.mailgun.net
- Add `o:testmode=yes` to check a send without delivering it
- Verify a custom domain first. The sandbox domain reaches only 5 authorised recipients

## What the review panel asked for

- Document recipient authorisation
- Publish send limits
- Publish SLA terms

## 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.