# Fix list: Pushover From Anchor Terminal's listing at https://www.anchorterminal.com/tools/pushover, the October 2026 research run, assessed 1 October 2026. Grade D, 53.3 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 Pushover: 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). Prices are public but per licence and seat, $4.99 once per platform or $5 per user a month for Teams, and capacity upgrades aren't priced on the page (10). A 30-day trial of the app and 10,000 free messages a month without a card (20). A person has to create an account and install the app to get a user key (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, 52 out of 100, up to 8.4 more on the total Why it scored 52: An application token and a user or group key, sent in the POST body rather than a header. An app token can only send, not read (18). No read access through the sending API, and group keys let you limit who receives (12). The sending API returns no untrusted content (10). Receipts for emergency messages and the limits endpoint, but no per-call log for the operator (6). Valid security.txt per the 30 September check. No disclosure policy, bug bounty or certification found beyond it (6). 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. Schema & documentation, 50 out of 100, up to 8.1 more on the total Why it scored 50: No OpenAPI or other machine-readable contract (0). No llms.txt and no Markdown docs (0). The single API page explains every parameter and when to use emergency priority, receipts and groups (16). Parameters are documented with limits (message 1,024 characters, title 250, URL 512, attachment 5 MB) and enumerated priorities and sounds, sent as form fields or JSON (11). Examples and an error example with `status`, `errors` and `request` fields (13). A /1/ version in the path and product changes announced on the blog, with no changelog as such (10). 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. ## 4. Reliability, 62 out of 100, up to 7.6 more on the total Why it scored 62: A status page at status.pushover.net (20). It renders in JavaScript and serves no feed we could find, so we couldn't read its history (5). Quotas published with numbers, 10,000 messages a month per account (25,000 for Teams) and at most 2 concurrent connections (15). Over-quota sends get 429, every response carries `X-Limit-App-Limit`, `X-Limit-App-Remaining` and `X-Limit-App-Reset`, and the docs say never to repeat a 4xx and to wait at least 5 seconds after a 5xx. There's no idempotency key, so a retry after a timeout can send twice (12). No SLA found (0). The /1/ API is generally available, not beta (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. Maintenance & community, 20 out of 100, up to 7 more on the total Why it scored 20: The last published API change is the 23 June 2026 blog post deprecating the GitHub notification endpoint, 100 days before this check (10). No releases or dated changes since then (0). A blog with dated product notices and a support site, with no public issue tracker (10). No official SDKs or MCP server (0). No packages to grade (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. Agent ergonomics, 64 out of 100, up to 5.9 more on the total Why it scored 64: Responses are a few fields, `status` and `request`, plus `receipt` for emergency messages (22). Little to page or filter, though a limits endpoint and the receipts API let an agent check state without guessing (10). Errors return an `errors` array naming the bad parameter, and the docs say which statuses to retry (18). No idempotency key, but emergency receipts can be polled and cancelled (6). Three required fields and sensible defaults, but no official SDKs (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. ## 7. Transparency & trust, 89 out of 100, up to 1 more on the total Made of editorial 77, provenance 100. Why it scored 89: Closed service under published terms (15). The privacy policy, updated 1 May 2026, says delivered messages are deleted once delivery is verified, undelivered ones after 21 days, server logs within 21 days and deleted accounts after 30 days (26). Dated notices on the blog, the per-account limit change announced on 8 April for 1 May and the GitHub endpoint retired by the end of 2026 after notice on 23 June (16). Nine processors named, from Apple and Google to Vultr and rsync.net, all data processed in the United States, and no third-party tracking (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. ## 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 incident history on status.pushover.net, which renders in JavaScript and serves no feed we could find - The price of capacity upgrades above 10,000 messages a month - Whether application tokens can be rotated without re-registering the application ## Weaknesses - Recipients need the app, $4.99 per platform after a 30-day trial - No idempotency key, so a retry after a timeout can send twice - No OpenAPI spec, llms.txt, official SDK or MCP server - No product change since the 23 June 2026 GitHub endpoint deprecation - At most 2 concurrent connections to the API ## 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 priority 2 with `retry` (30 or more) and `expire` (10,800 or less) when a person must act, then poll the receipt - Don't retry a 4xx. Fix the parameter named in `errors`. Wait at least 5 seconds before retrying a 5xx - Read `X-Limit-App-Remaining` before a batch. Over the monthly quota every send returns 429 - Keep messages to 1,024 characters and titles to 250 - Send to a group key to reach several people in one call. Each person still counts against the quota ## What the review panel asked for - Key route without the app - a readable status history ## 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.