Pushary by Pushary

# Fix list: Pushary

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/pushary, the October 2026 research run, assessed 1 October 2026. Grade D, 51.4 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 Pushary: 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, 20 out of 100, up to 16 more on the total

Why it scored 20: No public status page found (0) and no incident history (5). No rate limits published. The skill's limit of three notifications per task is advice to the agent, not a server limit (0). No 429 guidance, but the skill says to poll once, cancel a live question before asking it elsewhere and never build a retry loop (5 of 15). No SLA, and the terms say there's no guaranteed uptime (0). The hosted server is at version 1.4.1 with no beta label (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, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No machine payment protocol (0). Public plan prices, Agent at $9.99 a month with 5,000 notifications and Agent Pro at $19.99 with unlimited notifications and up to 5 people, but no per-call price (10). The 3-day trial takes a card up front, and the browser demo at pushary.com/try doesn't use the real service (0). Setup needs a person to pair a phone and start a paid account (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, 64 out of 100, up to 6.3 more on the total

Why it scored 64: One Bearer API key in the form `pk_xxx.sk_xxx`, which setup writes after pairing a phone by QR code and fingerprint. Partner customers enrol through scoped connection links instead of sharing the operator key (20 of 30). Enforced gates through Claude Code and Hermes hooks, and `propose_scope` with allowed and off-limits paths enforced on supported hosts. Plain MCP clients get cooperative questions only (15 of 20). The skill says a text answer containing yes isn't approval for a separate action (12 of 15). The audit trail records each question, the tool, who decided, when and under which policy, kept 30 to 365 days by plan (12 of 15). SECURITY.md promises acknowledgement within 48 hours for the skill repository and sends backend reports to the website. The security page covers encryption, HMAC-signed decision links and compliance recovery, but names no disclosure process, bounty or certification (5 of 20).

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. Schema & documentation, 73 out of 100, up to 4.4 more on the total

Why it scored 73: The registry entry types the remote and its auth header. The 6 tools are hosted and we couldn't list them without a key, but the skill documents every parameter (15 of 25). The skill files and llms-install.md are Markdown written for agents (10). The skill states when to ask, when to notify and when not to, in more detail than any other listing here (20). Question type is an enum of confirm, select and input, select takes 2 to 6 options, and delivery modes are named (10 of 15). Examples for each tool, and the outcome states (`pending`, cancelled, expired, missing, unavailable) are documented with what to do next (13 of 15). Versions in server.json and the skill, and changelogs on the adapter packages, but no changelog for the service (5 of 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.

## 5. Agent ergonomics, 76 out of 100, up to 3.9 more on the total

Why it scored 76: 6 tools (25). `list_sessions` is read-only, `wait: false` and `timeoutMs` shorten a call, nothing else needs paging (10 of 20). Every result carries `answered`, `status` and `handoffAction`, which tell the agent what to do next (18 of 20). `cancel_question` and a `correlationId` make re-asking safe, and we couldn't see annotations in the hosted tool definitions (8 of 20). Few required parameters, and official adapters in TypeScript and Python (15).

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.

## 6. Maintenance & community, 60 out of 100, up to 3.5 more on the total

Why it scored 60: The public repository synced from the private monorepo on 2026-10-01, and the registry entry is at 1.4.1 (30). The repositories show dated syncs every week, but no releases or dated release notes, so we give part credit for visible activity (5 of 20). Public issues welcome, and we didn't sample replies (8 of 25). server.json names `io.github.Pushary/pushary` and a GitHub OIDC workflow publishes it, so the namespace is verified by GitHub, but we couldn't query the registry to confirm the live record (12 of 15). The mirror holds docs and config only, and the adapters carry tests (5 of 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.

## 7. Transparency & trust, 63 out of 100, up to 3.2 more on the total

Made of editorial 71, provenance 55.

Why it scored 63: Closed hosted service under Estonian law with terms updated 2026-09-27, and MIT-licensed skill and adapters (18 of 30). The privacy policy (updated 2026-09-28) says open questions sit in a Redis cache for at most ten minutes, the audit trail is kept 30 to 365 days by plan (30 on Agent), notification subscriber data 7 to 180 days, source code and diffs aren't collected, and a DPA is available to Enterprise on request. The terms agree on at-least-once delivery and no uptime promise (25 of 30). Terms promise 30 days' notice of material changes when reasonably practicable, and we found no dated deprecation notices (8 of 20). Subprocessors are named with locations (Neon in Germany, Vercel, PostHog EU, Resend, Clerk, Stripe, Railway, FCM, APNs, RevenueCat), and primary infrastructure is in Germany (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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: pushary.com, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: could not be fetched (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 Pushary has a disclosure process for the hosted service beyond the skill repository's SECURITY.md. The security page doesn't name one.
- Whether the MCP registry serves the 1.4.1 record under io.github.Pushary/pushary.
- Whether the hosted tool definitions set `readOnlyHint` and `destructiveHint`.
- What price and terms apply to Partner use for your own customers.

## Weaknesses

- No free plan, and the 3-day trial takes a card up front
- Plain MCP clients get cooperative questions only, with no enforcement
- Wait times are set by the user's delivery mode, so an agent can't count on a long block
- No status page, SLA or service changelog, and the terms promise no uptime
- Partner use for your own customers has no public price

## 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.

- Read `answered`, `status` and `handoffAction` on every result, and never treat a timeout as approval
- Expect `ask_user` to return at once with `answered: false` when the user's mode is notify-only or terminal-only
- Poll `wait_for_answer` once (it waits at most 55 seconds), then follow the handoff instead of looping
- Cancel a live question with `cancel_question` before asking the same thing in chat
- Group open decisions into one `select` question, since each push interrupts the user

## What the review panel asked for

- dated service release notes
- a public status page
- backend disclosure policy
- enforcement without host hooks

## 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.