PostNitro

# Fix list: PostNitro

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/postnitro, the October 2026 research run, assessed 14 October 2026. Grade E, 44.5 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 PostNitro: 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. Security & auth, 30 out of 100, up to 12.3 more on the total

Why it scored 30: The MCP server runs OAuth 2.1 with PKCE S256, dynamic client registration and a revocation endpoint, but with one broad `postnitro` scope. Keys are `pn-` API keys sent in a header, generated in the web app, with no scopes or rotation documented (20). No read-only key or mode. Destructive tools are flagged in descriptions, drafts and the `DESIGN` output allow review, and the confirmation the Claude page describes is the client's, not the server's (4). Tools fetch article URLs and X posts as source material and return job logs and captions, with no injection guidance found (3). Per-job processing logs come back from the status endpoint. No account audit log was found (3). No security.txt, disclosure route, bug bounty or certification was found (0). The Claude page says tokens are scoped to one workspace and that Anthropic reviews directory connectors, which is a vendor claim and not scored.

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.

## 2. Reliability, 42 out of 100, up to 11.6 more on the total

Why it scored 42: Graded as a hosted service, the MCP server and the Embed REST API it wraps. No status page was found. `status.postnitro.ai` did not connect, `/status` returns 404, and only a health check at `mcp.postnitro.ai/health` answers (0). With no page there is no incident history to read (5). Limits are published per API key per minute, 5 for each create endpoint, 120 for status and output and 30 for the rest (15). The OpenAPI document gives 429 with `Retry-After` and `X-RateLimit` headers, and the combined generate-and-schedule tool returns the `designId` on a scheduling failure so a retry does not regenerate. No idempotency key is documented for writes (12). No SLA was found and the terms supply the service as is (0). Nothing is labelled beta or preview (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.

## 3. Payments & pricing, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Credit prices are public without a login at $0.04 a credit, 1 per imported slide and 2 per AI-written slide, with plan prices of $15, $30 and $60 a month (20). The web app has a free plan with no card, but agent access is not free. The MCP page, the agents page and the OpenAPI document say write calls return 402 without a paid plan, and only the API subscription page describes 5 free credits a month, so no free API tier is counted (0). A person signs up in a browser and generates a key, or approves OAuth in the client. Dynamic client registration removes the key step but not the signup (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.

## 4. Agent ergonomics, 49 out of 100, up to 8.3 more on the total

Why it scored 49: 35 MCP tools load together with no toolsets or read-only subset (5). The `DESIGN` output skips rendering and the `_and_wait` tools fold polling into one call, so 3 are added back (8). Templates and brands page with `page` and `limit` up to 100, and scheduled posts filter by date range and social account (14). Gateway errors carry `status` and a plain `message`, the schedule error page lists every validation message, and a missing ID returns the candidate IDs. A brand-limit error comes back as 401, which reads as an auth failure (14). No idempotency key. Destructive tools are named as such in their descriptions and audio deletion is refused while a post uses it. MCP annotations were not readable (6). Saved defaults and single-candidate auto-selection keep required arguments to one or two. Official code is a Node CLI and a browser editor SDK, one language (7).

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. Transparency & trust, 48 out of 100, up to 4.6 more on the total

Made of editorial 33, provenance 63.

Why it scored 48: Closed service under Terms of Service last updated 20 May 2024 that cover the APIs, allow changes or discontinuation without notice and take a perpetual licence to user content to run the service. The terms name no legal entity or governing law (12). The privacy policy, dated 5 October 2023, says carousel data is used to train PostNitro's AI model. The Claude connector page and the policy's own page description say content is never used for training. Deletion within 24 hours of a request is stated in both the terms and the policy. No DPA (8). The fact sheet dates the withdrawal of the Creator and Team plans and existing subscribers keep them. The CLI changelog marks API-version dependencies. No deprecation policy for the API (8). The policy names UserMaven and CrispChat and an unnamed payment processor, the docs name Lemon Squeezy for billing, and no data locations were found (5).

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: postnitro.ai, registered 2023-03-23 (3 years) (7 of 15)
- Terms of service: read, states 5 of the 7 things a reader expects, and has 1 clause that costs points (6.3 of 10)
- Privacy policy: read, states 4 of the 8 things a reader expects, and has 1 clause that costs points (5 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 6. Schema & documentation, 77 out of 100, up to 3.7 more on the total

Why it scored 77: OpenAPI 3.1 document for the Embed API at `/.well-known/openapi/embed.json` with 13 operations. It leaves out the documented template, brand and AI-preset endpoints, `llms.txt` links an older 6-operation spec, and the MCP tool schemas need a key to list (20). `llms.txt`, `llms-full.txt`, a docs `llms.txt`, `.md` twins and Markdown by content negotiation on every page (10). The docs state what each tool is for, when not to use PostNitro (plain publishing, X, analytics) and the `embedPostId` and `designId` split. The docs index still says 12 MCP tools and four scheduling networks, and pages disagree on the free tier (15). 24 enums, typed slide objects and per-platform settings objects with conditional rules (12). Examples on each page and a full table of validation messages for the Schedule API (13). `info.version` 1.0.0 with no version in the path and no API changelog. The CLI has a dated Keep a Changelog file with semver (7).

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, 65 out of 100, up to 3.1 more on the total

Why it scored 65: CLI 1.5.0 on 7 October 2026, and `llms.txt` and the fact sheet are dated 7 October 2026 (30). CLI 1.3.0 on npm on 18 August, 1.4.1 on 29 September and 1.5.0 on 7 October, with Facebook and Pinterest scheduling added, and the Cursor plugin on 29 September (20). Closed service with a dated CLI changelog, support by email and in-app chat, and four public repositories with no open issues and few outside contributions to judge replies by (8). The server card names `ai.postnitro/mcp`, but the official MCP registry returned no PostNitro entry (0). The CLI publishes from a GitHub Actions workflow. The Embed SDK was last published on 15 July 2025 (7).

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.

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- Conflicting training statements on PostNitro's own pages, read 14 October 2026. The privacy policy body (5 October 2023) says the data saved from carousel creation is used to train PostNitro's AI model, while the same page's description and the Claude connector page say content is never used to train AI models. At least one is wrong, and no dated update settles it (-2) (https://postnitro.ai/privacy, https://postnitro.ai/claude)

## 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 input schemas and annotations, which need a key or OAuth sign-in to list
- unchecked: the Claude Connector Directory listing, which answered 403, and the ChatGPT plugin listing
- unchecked: the Product Hunt launch on 13 October 2026. producthunt.com answered 403
- Whether the API has a free tier. The subscription docs give 5 credits a month with no card, while the MCP page, agents page and OpenAPI document say write calls need a paid plan
- Whether the 3-day trial on Creator+ needs a card and includes API credits
- The MCP server version. The server card and docs say 1.0.0 and the health check reports 1.3.0
- firstReleased is 11 August 2025, the n8n node's v0.1.0 against the Embed API, with the API docs archived on 13 August 2025. The MCP server is first seen on 15 April 2026 and the Embed SDK on npm on 18 March 2024
- The fact sheet asks directories to treat it as authoritative where other sources disagree. Recorded as a fact and not acted on
- Which training statement holds. The privacy policy body says carousel data trains PostNitro's AI model, and the page description and the Claude page say it never does. A dated policy update that settles it would remove the deduction

## Weaknesses

- No status page, incident history, SLA, security.txt or certification was found
- 35 MCP tools load at once, with no toolsets or read-only subset, and the OAuth flow has one broad `postnitro` scope
- The privacy policy says carousel data trains PostNitro's AI model, while the Claude connector page says content is never used for training
- No idempotency key on create or schedule calls, and the Embed API has no changelog or deprecation policy
- Pages disagree on the API free tier and tool count. One docs index still says 12 MCP tools and four scheduling networks

## 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.

- Call `postnitro_set_defaults` once with a template, brand and AI preset, or every generate call must carry those IDs
- Pass the `designId` from `postnitro_get_output` to scheduling, never the `embedPostId`, or the call fails with `Design not found`
- For a LinkedIn PDF post, set `linkedinPostSettings.postType` to `document` with a 5 to 90 character `postTitle`
- Ask for the `DESIGN` output or save as `DRAFT` when a person must approve before anything publishes
- Keep to 5 create calls a minute per key and wait for `Retry-After` on a 429

## 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.