# Fix list: Upload-Post API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/upload-post, the October 2026 research run, assessed 1 October 2026. Grade C, 58.9 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 Upload-Post 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. Security & auth, 32 out of 100, up to 11.9 more on the total Why it scored 32: One account API key sent as Apikey or Bearer in a header, no query-string option, no scopes, and the docs advise generating a new key periodically without describing revocation. The MCP's OAuth 2.1 (PKCE and dynamic registration) has a single mcp.full scope that resolves to the account key. JWT connect links let end users link accounts without seeing the key (18). No read-only key or scope, though the annotations mark the 13 destructive tools (6). get_post_comments, list_dm_conversations and get_google_business_reviews return text from strangers, and we found no prompt-injection guidance in the docs or tool descriptions (0). get_history and get_status show past uploads and request results, no audit log (5). No security.txt, disclosure route or certification. npm releases publish with provenance through OIDC (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. ## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402 or other machine payment (0). Plan prices are public, with FFmpeg minutes and Shorts analyses per plan and a $19 a month X link add-on, but no per-call price (10). Free plan of 2 profiles and 10 uploads a month without TikTok, no card (20). A person has to sign up in a browser for the key, or approve OAuth in a client (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. Reliability, 57 out of 100, up to 8.6 more on the total Why it scored 57: An own status page at upload-post.com/status that describes per-platform availability and uptime history, but loads its data by script and showed our reader only Loading status, so we couldn't see components (15). No readable incident history (5). X-RateLimit-Limit, Remaining and Reset headers, daily caps per account per network (Instagram 50, TikTok 15, YouTube 10, LinkedIn 20) and per-plan request limits per the 30 September check (15). The rate-limits guide says to wait for X-RateLimit-Reset, back off exponentially and send an Idempotency-Key on every upload, though the error guide and spec don't mention the key and there's no Retry-After (12). No SLA, and the terms disclaim uninterrupted service (0). GA (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. ## 4. Agent ergonomics, 72 out of 100, up to 4.6 more on the total Why it scored 72: 59 MCP tools with no toolsets or dynamic loading (5). Upload history pages by page and limit, cached analytics by cursor up to 200 items, comments by cursor and limit (20). Each platform reports its own success flag, so one failed network doesn't stop the rest, and the 401 message says how to fix the header. No error codes (14). An Idempotency-Key is recommended for uploads, and every MCP tool carries readOnlyHint and destructiveHint, 13 of them marked destructive (18). Official Python and Node SDKs, and platform defaults to instagram on several tools (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. ## 5. Schema & documentation, 81 out of 100, up to 3.1 more on the total Why it scored 81: OpenAPI 3.0.1 at docs.upload-post.com/openapi.json with 22 paths, fewer than the API's documented surface, and zod input and output schemas on all 59 MCP tools in source (22). llms.txt indexing about 80 pages, plus llms-full.txt (10). Tool descriptions in source say which IDs each network needs and when to add a parameter rather than reach for another tool (17). Enums, defaults and bounds such as limit 1 to 50 on comments (14). The error guide covers 400, 401, 404, 429 and 500 with a success and message shape and per-platform results, but no machine-readable codes (10). No API changelog. The MCP repo cuts GitHub releases with generated notes and PyPI shows dated versions (8). 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. ## 6. Transparency & trust, 73 out of 100, up to 2.4 more on the total Made of editorial 78, provenance 68. Why it scored 73: Closed API under clear terms from TONVI TECH SL (CIF B-19780394, Málaga), version 2.5 updated 29 August 2026, with the MCP server and both SDKs under MIT (20). The privacy policy updated 4 September 2026 gives retention per data type, from 30 days for backups and 90 days for logs, DMs and comments to 6 years for invoices, and links a DPA (30). The terms promise at least 30 days' notice of material changes. No API deprecation policy (8). Subprocessors named with countries, Hetzner in Germany for primary hosting, and the policy says full videos go to Google Gemini for the Shorts analyser (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: upload-post.com, registered 2024-11-02 (1 year) (3 of 15) - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 79 out of 100, up to 1.8 more on the total Why it scored 79: MCP tag v0.11.4 on 27 September 2026 and a 0.11.5 commit on 1 October, Python SDK 2.13.0 on 9 September (30). 16 MCP tags on commits since 9 July and four Python SDK releases since 20 July (20). The MCP repo has had 14 pull requests, and commits landed in 11 of the last 13 weeks. robots.txt kept us from the issue tracker, and there's no public API changelog (10). Official registry entry com.upload-post/mcp under its own domain, latest 0.10.0 on 3 September (15). A publish workflow with npm provenance but no test CI, and npm's latest tag read 0.11.1 while git tags run to v0.11.4 (4). 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. ## 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: status history, since the status page loads its data by script - Why npm's latest tag for @upload-post/mcp read 0.11.1 when git tags run to v0.11.4 - Whether API keys can be revoked or limited. The docs say only to generate new ones periodically - Whether the Idempotency-Key the rate-limits guide recommends is honoured on every upload endpoint, since the spec and error guide don't mention it - unchecked: open GitHub issues and reply times, since robots.txt blocked our reader ## Weaknesses - One account key with no scopes, and the MCP's OAuth grants a single mcp.full scope - 59 MCP tools with no toolsets or read-only subset - Comment, DM and Google Business review tools return untrusted text with no injection guidance - OpenAPI spec covers 22 paths and no API changelog - Free plan excludes TikTok and X link posts need a $19 a month add-on ## 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. - Send `Authorization: Apikey ` on REST. The MCP also takes Bearer - Use async_upload=true for video, then poll the upload status endpoint every 5 to 60 seconds, not faster - Send an Idempotency-Key on every upload so a timed-out retry doesn't post twice - Check each platform's success flag in results, because one network failing doesn't stop the others - Wait until X-RateLimit-Reset after a 429, and mind daily caps such as TikTok 15 and YouTube 10 per account ## What the review panel asked for - Idempotency-Key in the spec - Scoped or read-only keys - read-only scope - document key revocation ## 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.