Resend API + MCP by Resend

# Fix list: Resend API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/resend, the October 2026 research run, assessed 1 October 2026. Grade BB, 75.3 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 Resend 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, 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 ($0.90 down to $0.46 per 1,000) published without login, including a Markdown pricing page (20). Free plan of 3,000 emails a month, 100 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, 65 out of 100, up to 6.1 more on the total

Why it scored 65: Bearer keys with full_access or sending_access, and a sending key can be limited to one domain. The hosted MCP signs in by OAuth with no documented scope choice (25). Sending-only keys exist, but the MCP has no read-only mode, and with a full key an agent can create keys and remove domains (10). get-received-email hands inbound mail bodies to the model, and we found no prompt-injection guidance in the MCP docs or README (0). API request logs with full request and response bodies (14). SOC 2 Type II, an annual penetration test, a responsible-disclosure page and a security.txt without an Expires field (16).

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. Agent ergonomics, 67 out of 100, up to 5.4 more on the total

Why it scored 67: 106 tools with no toolsets or filtering, and about 260 KB of tool source behind them (5). limit with after and before cursors on every list (20). Typed errors such as daily_quota_exceeded and invalid_idempotent_request, though a raw call without a User-Agent gets a 403 (17). `Idempotency-Key` on sends. readOnlyHint on 45 tools, but none of the 16 remove, cancel, revoke or rotate tools carries destructiveHint (12). SDKs in Node, Python and other languages, and the MCP takes a default sender and reply-to (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.

## 4. Reliability, 85 out of 100, up to 3 more on the total

Why it scored 85: incident.io status page with per-component uptime (20). Thirteen incidents between 3 September and 1 October, including elevated API errors on 1 October, intermittent API errors on 24 September, delayed sending on 16 September (about 9,200 emails held up to 25 minutes) and an unresponsive remote MCP server on 11 September. The page shows no durations for most of them and nothing before 3 September, so we can't call any of them a major outage, but it's more than a minor-only month (15). 10 requests a second per team, plus daily and monthly quotas (15). 429 with `retry-after` and IETF ratelimit headers, and `Idempotency-Key` on POST /emails and /emails/batch, kept 24 hours (15). 99.99% uptime SLA on Enterprise (10). 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.

## 5. Transparency & trust, 85 out of 100, up to 1.3 more on the total

Made of editorial 70, provenance 100.

Why it scored 85: Closed service with published terms and an MIT MCP server (20). 30-day retention on Free, Pro and Scale, backups kept 7 days, a DPA and a privacy policy (24). Dated changelog, no deprecation policy found (8). 22 subprocessors listed, all in the USA, updated 27 August 2026, including Anthropic and RunPod for AI processing. Hosting regions aren't stated (18).

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.

## 6. Schema & documentation, 95 out of 100, up to 0.8 more on the total

Why it scored 95: OpenAPI spec in resend/resend-openapi and typed Zod schemas on every MCP tool (25). llms.txt with about 400 links, Markdown docs and a Markdown pricing page (10). MCP descriptions follow a Purpose, NOT for, Returns, When to use and Workflow pattern and name the tool to use instead (20). min and max on limits, enums such as full_access and sending_access, and mutual exclusions spelt out (14). An errors page with typed error names, and examples throughout (14). Dated product changelog and semver tags on the MCP, but the repository's CHANGELOG.md stops at 1.1.0 and the API has no version in its path (12).

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.

## 7. Maintenance & community, 93 out of 100, up to 0.6 more on the total

Why it scored 93: resend-node v6.32.0 on 1 October and MCP v2.24.0 on 29 September (30). 18 MCP tags since 3 July and six Node SDK releases since 11 September (20). Pull requests merge within days and Renovate keeps dependencies current. We couldn't see issue reply times from git (18). Current official SDKs (15). CI builds, lints, checks pinned dependencies and runs the MCP tests (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.

- Incident durations, and anything before 3 September, on the status page
- OAuth scopes on the hosted MCP, if any
- Whether failed or rejected sends count against the quota
- Issue reply times on the MCP repository

## Weaknesses

- 106 MCP tools load at once, with no toolsets
- No destructiveHint on the 16 remove, cancel, revoke and rotate tools
- Received mail reaches the model through the MCP with no prompt-injection guidance
- 13 status incidents between 3 September and 1 October
- 10 requests a second per team by default

## 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.

- Send an `Idempotency-Key` on POST /emails so a retry after a timeout doesn't send twice
- Send a User-Agent header on raw HTTP calls or you'll get a 403
- Give the agent a `sending_access` key limited to one domain unless it has to manage the account
- On 429, wait for `retry-after`, and use /emails/batch to stay under 10 requests a second
- Verify a domain before sending to anyone but your own address

## What the review panel asked for

- Toolsets on the MCP
- Destructive hints
- a written deprecation policy
- release notes per MCP tag
- add MCP toolsets
- billing for rejected sends
- toolsets or filtering
- destructive hints on removals
- toolsets on the MCP
- incident durations
- read-only MCP mode
- OAuth scopes
- Add programmatic signup
- Publish incident durations
- Show history before September

## 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.