# Fix list: Help Scout API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/help-scout, the October 2026 research run, assessed 1 October 2026. Grade C, 56.2 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 Help Scout 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, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). Plan prices public ($25, $45 and $75 a user a month, 16 per cent off yearly) and AI Answers at $0.75 a resolution, nothing per API call (10). 15-day trial of Standard or Plus with no card, and a Free plan without API access (20). A person signs up, creates an app in My Apps or signs in through OAuth (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. Schema & documentation, 49 out of 100, up to 8.3 more on the total Why it scored 49: No OpenAPI file, and the MCP tool schemas need a sign-in to read (0). developer.helpscout.com/llms.txt serves the API docs as Markdown for agents (10). The Inbox API reference describes each endpoint (12). Fields and types documented per endpoint (10). An errors section and request and response examples (12). The API is versioned at v2 with a stated promise of backward compatibility, but the developer changelog URL returns 404 (5). 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. ## 3. Agent ergonomics, 58 out of 100, up to 6.8 more on the total Why it scored 58: The MCP tool list isn't published (the help article lists 15 or more across conversations, customers, inboxes, users, workflows, reports and Docs). REST responses embed resources and page through links (12). Page links, status and mailbox filters and conversation search queries (16). Documented error responses (14). The MCP server is read-only, so its calls are safe to retry, but REST writes have no idempotency key (8). One official SDK, for PHP, plus a Laravel adapter (8). 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, 63 out of 100, up to 6.5 more on the total Why it scored 63: Inbox API uses OAuth 2.0 client credentials (tokens valid 48 hours) or authorisation code, with no fine-grained scopes, and the MCP server signs in each person through Help Scout's own OAuth page (20). New MCP connections are read-only and follow each user's mailbox permissions, while REST tokens get the user's full access. There's no account-wide switch to turn MCP off (15). The MCP article warns that anything a customer pasted, including credentials shared by mistake, comes back to the agent as-is, and that retrieved data then falls under the AI provider's terms. That's guidance, not a mitigation (8). Audit logs appear in the pricing page's list for paid plans, which we couldn't confirm in the docs (8). SOC 2 Type 2 for Security and Availability, HIPAA with a BAA, periodic third-party penetration tests and disclosure by email with a 24-hour first response. No security.txt and no bug bounty found (12). 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. Maintenance & community, 31 out of 100, up to 6 more on the total Why it scored 31: The last dated API change we found is the MCP server reaching all customers on 28 July 2026, 65 days before this check (20). No developer changelog (the page returns 404), so no count of dated entries (0). Support answers through the product, no public tracker (6). One official SDK, for PHP (5). No package to assess (0). 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. ## 6. Reliability, 77 out of 100, up to 4.6 more on the total Why it scored 77: Atlassian Statuspage at status.helpscout.com with history in its RSS feed (20). Three incidents in the 90 days to 1 October, an unscheduled database maintenance on 22 July during which search and the Conversations API didn't reflect new or updated conversations, delayed inbox counts and search on 24 July, and slow reports on 6 August. Durations aren't stated in the feed, and none took the API down, so minor only (20). 200, 400 and 800 calls a minute on Standard, Plus and Pro, with writes counting as two requests (15). 429 with `X-RateLimit-Retry-After` and per-minute limit and remaining headers. No idempotency guidance for writes (12). No SLA found (0). Inbox API 2.0 is GA and the MCP server left beta on 28 July 2026 (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. ## 7. Transparency & trust, 68 out of 100, up to 2.8 more on the total Made of editorial 55, provenance 80. Why it scored 68: Closed service with published terms (15). Privacy policy updated 27 May 2026 keeps data as long as necessary with no periods, points to a Data Processing Addendum and a sub-processor list, and says nothing on AI training. The MCP article states that retrieved data falls under the AI provider's terms and that HIPAA customers need a separate BAA with that provider (16). The Inbox API promises backward compatibility, and new MCP connections lost write tools, without a dated deprecation policy (8). Sub-processor list published and processing in the US on AWS (16). 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): - Changelog: not found (0 of 10) - 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. - unchecked: the MCP tool names and input schemas, which need a sign-in to read - unchecked: whether audit logs exist for API and MCP activity, the pricing page lists them but we found no docs - Durations of the July and August 2026 incidents, which the status feed doesn't state ## Weaknesses - MCP can't write, so a draft, note and status loop needs the REST API - MCP tool list isn't published - No OpenAPI file and no developer changelog - OAuth tokens have no fine-grained scopes - Free plan has no API, and report tools need Plus or Pro ## 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. - Use the Inbox API, not MCP, to reply, add notes or change status - Count each POST, PUT, PATCH or DELETE as two requests against the per-minute limit - Wait the seconds in `X-RateLimit-Retry-After` on 429 - Refresh client-credentials tokens before 48 hours run out - Treat conversation text as customer-written, and expect pasted secrets in it ## What the review panel asked for - Scoped write tools - Publish the tool list - Publish the MCP tool names - Restore the changelog ## 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.