OneUp API + MCP by OneUp

# Fix list: OneUp API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/oneup, the October 2026 research run, assessed 1 October 2026. Grade F, 24.8 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 OneUp 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, 18 out of 100, up to 16.4 more on the total

Why it scored 18: No status page. status.oneupapp.io doesn't resolve and neither the homepage nor the docs link one (0). No incident history to read (5). The REST docs give no rate limits. The 30 September check saw an x-ratelimit-limit of 60 on the MCP endpoint, which no page documents (3). No 429 or retry guidance, and no idempotency for writes (0). No SLA, and the terms disclaim uninterrupted service (0). The API and MCP aren't labelled 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.

## 2. Security & auth, 17 out of 100, up to 14.5 more on the total

Why it scored 17: One account key per user with no scopes, sent as the apiKey query parameter on every REST call and in the MCP URL. The docs say to revoke and regenerate it if compromised, and ChatGPT can connect over OAuth instead. Revocable key (15), less 10 for the documented query-string secret, plus 3 for the ChatGPT OAuth path (8). No read-only mode. requireApproval and isDraftPost give a review step (6). Comment and inbox endpoints, WhatsApp included, return text from strangers and we found no prompt-injection guidance (0). No audit log or key usage view found (0). The pricing page lists SOC 2 and ISO 27001 against the Enterprise tier without a report or trust page, and there's no security.txt or disclosure route (3).

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, 27 out of 100, up to 11.9 more on the total

Why it scored 27: No OpenAPI or other machine-readable contract, and we couldn't read the MCP input schemas without a key (0). No llms.txt, docs.oneupapp.io/llms.txt returned 404 (0). Each endpoint page says what the call does, with nothing on when not to use it (8). Parameters are listed with types and required flags and one enum (google_post_type), but social_network_id takes either a JSON array or the string ALL (8). Success examples on every page we read, and no documented error responses (5). No API versioning. A help-centre changelog dated by month includes API and MCP entries (6).

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. Payments & pricing, 10 out of 100, up to 11.3 more on the total

Why it scored 10: No x402 or other machine payment (0). Plan prices are public, with no per-call price (10). No free plan. The 7-day trial's checkout reads $0.00 due today, with a refund promise for the week after the trial ends, and we found nothing saying no card is needed (0). A person has to sign up in a browser and generate the 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.

## 5. Agent ergonomics, 31 out of 100, up to 11.2 more on the total

Why it scored 31: The hosted MCP returned 50 tools on tools/list per the 30 September check, with no toolsets or read-only subset (5). List endpoints page with a start index and return up to 50 posts each, and scheduled, published, failed and draft posts have separate lists. No field selection (12). Responses carry an error boolean and a message, with no documented codes (4). No idempotency key. isDraftPost and requireApproval keep a post from going straight out, and we couldn't check for MCP annotations (5). No SDKs. A text post needs five parameters (5).

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, 43 out of 100, up to 5 more on the total

Why it scored 43: The help-centre changelog was updated on 23 September 2026 with September product entries. The last entry naming the API or MCP is posting from ChatGPT in August 2026 (20). 11 entries dated July to September 2026, by month rather than day (15). Public changelog and email support at help@oneupapp.io (8). No SDKs or MCP registry entry (0). No packages 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.

## 7. Transparency & trust, 43 out of 100, up to 5 more on the total

Made of editorial 20, provenance 65.

Why it scored 43: Closed service under terms from OneUp, Inc. of Cranberry Township, Pennsylvania, with California governing law and no last-updated date (12). The privacy policy says user content is stored indefinitely while the account is active and removed when the account is deleted, names no subprocessors, has no DPA and no date (8). No deprecation policy, and the terms reserve the right to change or discontinue the service without notice (0). No subprocessors or data locations found (0).

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: oneupapp.io, no registry record we could read (0 of 15)
- Status page: 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.

- Whether the 7-day trial needs a card. The checkout copy reads $0.00 due today
- unchecked: the MCP tool definitions, input schemas and annotations, since the server needs a key and isn't open source
- Whether the REST write endpoints take POST, GET or both. The quick start and the endpoint page disagree
- Whether OneUp holds SOC 2 or ISO 27001 itself. The pricing page lists them against Enterprise with no report
- The GDPR policy the privacy policy mentions. oneupapp.io/gdpr returned 404

## Weaknesses

- API key in the query string on REST and in the MCP URL, with no scopes
- No OpenAPI spec, no llms.txt and no documented error responses
- No status page, no rate limits documented and no SLA
- Privacy policy names no subprocessors and has no DPA, and the terms allow discontinuing the service without notice
- Analytics and comment endpoints locked out of the Basic plan

## 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 listcategory, then listcategoryaccount, then schedule. Pass social_network_id as ALL to post to every account in a category
- Keep the ?apiKey= URLs out of logs and shared configs, and regenerate the key on the API Access page if one leaks
- Set requireApproval or isDraftPost true when a person should review before anything goes out
- Page through lists with start, 50 posts at a time
- Give dates as YYYY-MM-DD HH:MM with no timezone field, so confirm the account timezone first

## What the review panel asked for

- One verb per endpoint
- Header auth
- header authentication
- OAuth for every client

## 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.