# Fix list: Postmark API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/postmark, the October 2026 research run, assessed 1 October 2026. Grade B, 66.7 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 Postmark 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, 60 out of 100, up to 8 more on the total Why it scored 60: Status page at status.postmarkapp.com (Sorry) with monthly history (20). Since July, sending delays of 18 minutes on 28 September and 20 minutes on 22 September with mail queued and not lost, sending delays on 15 August, inbound and webhook delays, 70 minutes of web-app errors on 17 September, and planned hour-long maintenance on 27 July and 7 August. Minor only (20). Batch limits are published (500 messages, 50 MB a call) but no request-rate limit (5). A 429 is documented with advice to reduce the rate, with no Retry-After and no idempotency key for sends (5). No SLA found on the pricing page (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). Prices and per-1,000 overage ($1.80, $1.30, $1.20) published without login (20). Developer plan of 100 emails a month with no card (20). Browser signup and a manual account review before sending outside your own domains (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, 63 out of 100, up to 6.5 more on the total Why it scored 63: Server tokens limited to one server and a separate account token for account-level calls, plus IP allowlisting for API sending since 27 August and 2FA on every plan since 23 September. No per-scope tokens (22). A server token can't reach other servers, the MCP annotations let clients confirm writes, and `WEBHOOK_URL_ALLOWLIST` limits where createWebhook can point (12). The MCP README names the prompt-injection risk and the controls (dedicated token, client approval, the allowlist). Bounce dumps carry text from remote servers (12). Message activity kept 45 days, and the MCP writes one JSON log line per call with addresses masked (12). The security page names a SOC 1 data centre and HTTPS, but no SOC 2 or ISO 27001 of Postmark's own, no disclosure policy and no security.txt (5). 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. Agent ergonomics, 79 out of 100, up to 3.4 more on the total Why it scored 79: 24 tools and no toolsets (15). count and offset with the 10,000 cap stated in the descriptions, filters on searches, and a truncation notice when listTemplates hits 100 (17). Over 40 documented error codes, and startup errors name the missing variable and link to the fix (18). Every tool carries readOnlyHint, destructiveHint and idempotentHint, with 12 read-only and the deletes flagged destructive. No idempotency key for sends (15). DEFAULT_SENDER_EMAIL and DEFAULT_MESSAGE_STREAM cut required fields, and there are official Node and Python SDKs (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. ## 5. Schema & documentation, 81 out of 100, up to 3.1 more on the total Why it scored 81: No OpenAPI spec for the REST API. Every one of the 24 MCP tools has a typed Zod schema, so half (15). llms.txt of about 1,100 lines with code samples (10). MCP descriptions state the purpose and point to the right alternative, such as 'Use sendBatch to send multiple distinct messages' (16). Typed inputs with email validation, a 50-recipient cap and the 22 bounce types as an enum (13). More than 40 JSON error codes grouped by area, with examples (14). Dated product updates and a semver CHANGELOG for the MCP server, but no API versioning (13). 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. Maintenance & community, 65 out of 100, up to 3.1 more on the total Why it scored 65: postmark-python v0.4.0 on 12 August and an API change (IP allowlisting) on 27 August, so within 90 days (20). Python 0.3.6, 0.3.7 and 0.4.0, MCP 2.1.1 on 13 July and three product updates since 27 August (20). Updates are public and support answers by ticket. We couldn't see issue replies (10). The Python SDK is current, while the Node SDK's last tag is 4.0.7 from 18 February with July commits unreleased (10). The MCP repository has tests but no CI, which its own CHANGELOG lists as planned (5). 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, 80 out of 100, up to 1.8 more on the total Made of editorial 69, provenance 90. Why it scored 80: Closed service with published terms and an MIT MCP server (20). Message content and metadata deleted after 45 days, retention adjustable from 7 to 365 days, suppressions kept indefinitely, and a DPA with standard contractual clauses built into the terms (26). No deprecation policy or dated deprecation notices found (5). Two named subprocessors, Deft near Chicago and AWS, US hosting only, with change notifications (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. Provenance checks not met in full (half of this category, computed from checked facts): - security.txt: not found (0 of 10) ## 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 ActiveCampaign's SOC 2 or ISO 27001 reports cover Postmark. Postmark's own security page names none - Published request-rate limits, if any - Whether Postmark has an SLA on any plan ## Weaknesses - No OpenAPI spec and no published request-rate limit - Manual account approval before sending outside your own domains - No SOC 2, ISO 27001, disclosure policy or security.txt found for Postmark itself - Webhooks aren't HMAC-signed - The MCP server runs locally only and its repository has no CI ## 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. - Install @activecampaign/postmark-mcp, never the unscoped postmark-mcp package - Use the token `POSTMARK_API_TEST` to check a payload without sending - Set `MessageStream` to `outbound` for transactional mail and a broadcast stream for bulk - Set `WEBHOOK_URL_ALLOWLIST` so a misled createWebhook call can't send events to someone else's server - Keep `count + offset` under 10,000 on message and bounce searches ## What the review panel asked for - Clarify test token accounts - Publish a request-rate limit - 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.