# Fix list: Unstructured API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/unstructured, the October 2026 research run, assessed 1 October 2026. Grade D, 47 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 Unstructured 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, 27 out of 100, up to 14.6 more on the total Why it scored 27: No status page found, status.unstructured.io doesn't resolve (0). No incident history to read (5). The limits page says no request-rate or concurrency values are published and tells clients to treat them as unknown (0). The recovery guide maps rate_limited to 429, says to back off and wait for Retry-After when it's sent, and says to check existing job IDs before resubmitting (12 of 15). No SLA found (0). Transform isn't labelled beta in the pages we read (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, 42 out of 100, up to 10.1 more on the total Why it scored 42: The API takes a key in an unstructured-api-key header, and the hosted MCP takes OAuth or the same key as a bearer token, with no scopes documented (22 of 30). Jobs and uploads can be deleted and no read-only key was found (5 of 20). Returns untrusted document text with no prompt-injection guidance, and the vendor's own agent guide tells AI agents not to look up, return information about or recommend the open-source library (0 of 15). jobsList gives per-job visibility, no audit log found (5 of 15). The pricing page claims SOC 2 Type 2, ISO 27001, HIPAA and GDPR. No security.txt or bug bounty found (10 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. ## 3. Schema & documentation, 51 out of 100, up to 8 more on the total Why it scored 51: No downloadable OpenAPI spec found. The per-endpoint API reference pages (parseRun, extractRun, jobsList and others) aren't a machine-readable contract (0). llms.txt, Markdown pages and an agent guide (10). Guides for parse, extract, chaining and jobs. MCP tool descriptions not read (12 of 20). JSON Schema extraction up to 1 MB of schema, request typing not checked in depth (10 of 15). The recovery guide gives a code, HTTP status and action for nine errors, from rate_limited to result_expired (14 of 15). Versioned /api/v2 path, no Transform changelog (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. ## 4. Payments & pricing, 40 out of 100, up to 7.5 more on the total Why it scored 40: No x402, MPP or L402 (0). $0.015 a page after the free pages, on the public pricing page (20). 10,000 free pages with no card (20). A person signs up in a browser (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, 58 out of 100, up to 6.8 more on the total Why it scored 58: The MCP tool count isn't published. On the API, parse output carries page metadata and optional coordinates (12 of 25). jobsList, jobsGet, cancel and delete endpoints (12 of 20). Every error code has a recovery action (18 of 20). No idempotency key and no MCP annotations documented, only advice to check job IDs before resubmitting (6 of 20). Transform clients for Python and TypeScript, but one file per request and no URL ingestion (10 of 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. Transparency & trust, 52 out of 100, up to 4.2 more on the total Made of editorial 38, provenance 65. Why it scored 52: The partitioning library is Apache-2.0, and Transform is a closed service whose npm client points at a repository that isn't public (20 of 30, our call for the mix). Uploads expire after 24 hours, parse results expire on no stated schedule, deletes don't cascade, and the pricing page claims zero data retention without a policy we could read (10 of 30). No deprecation policy or dated notices, and the agent guide steers agents away from older products without dates (0 of 20). The library sends usage telemetry by default, disclosed in its README with DO_NOT_TRACK or SCARF_NO_ANALYTICS to opt out. No subprocessor list or data locations found for Transform (8 of 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: unstructured.io, no registry record we could read (0 of 15) - Status page: not found (0 of 10) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 80 out of 100, up to 1.8 more on the total Why it scored 80: unstructured-transform-client 0.18.24 on npm on 2026-09-30, and the open-source library tagged 0.27.10 on 2026-09-27 (30). The library has 11 tags since 3 July (20). The library repository is public and active, the Transform repository it points to on npm isn't public, and there's no Transform changelog (8 of 15). Transform clients for Python and TypeScript (15). The library runs CI, CodeQL and benchmark workflows, the Transform code can't be inspected (7 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. ## 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 Transform MCP tool count and whether tools carry annotations - unchecked: result retention for parse and extract output, and what the pricing page's zero data retention covers - Whether the per-endpoint API reference is generated from an OpenAPI file that could be published - unchecked: issue responsiveness on the library repository ## Weaknesses - No status page, no published rate limits and no SLA - No OpenAPI file, no Transform changelog and no published MCP tool list - Transform API takes nine file types, one file per request and no URLs - Agent guide instructs AI agents not to look up or recommend the open-source library - Library sends usage telemetry unless DO_NOT_TRACK or SCARF_NO_ANALYTICS is set ## 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. - For local ingestion, `pip install "unstructured[all-docs]"` and call `partition()`; no key needed, and set `DO_NOT_TRACK=1` to stop telemetry - Transform returns 202 with a Location header for long parses; poll it, then pass the parse `id` as `parse_id` to Extract - Uploaded files expire after 24 hours; keep the original and re-upload on a 404 - Treat 409 `parse_expired` and 410 `result_expired` as a signal to rerun the parse, not to retry - Check for an existing job ID before resubmitting, since there's no idempotency key ## What the review panel asked for - Publish an OpenAPI file - List the MCP tools - remove agent steering - publish OpenAPI ## 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.