{
  "fixes": {
    "slug": "foxit-pdf-services",
    "name": "Foxit PDF Services API",
    "listing": "https://www.anchorterminal.com/tools/foxit-pdf-services",
    "markdown": "# Fix list: Foxit PDF Services API\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/foxit-pdf-services, the October 2026 research run, assessed 8 October 2026. Grade D, 48.3 out of 100.\n\nThis 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.\n\nFor a coding agent working on Foxit PDF Services API: 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.\n\n## 1. Reliability, 47 out of 100, up to 10.6 more on the total\n\nWhy it scored 47: Read with the hosted lines. status.foxit.com keeps 90-day component history for Foxit's cloud products, but has no component for the API gateway at na1.fusion.foxit.com or for PDF Services (8 of 20). With no component there is no readable incident history for this API (5). Rate limits are published as 15 requests a minute in sandbox mode and 100 in production mode, per application, over a rolling 60 seconds (15). The limits guide asks for exponential backoff on 429 and the credits guide says a retried request is not charged twice, but no Retry-After header is documented and 429 also signals an exhausted credit quota (9 of 15). The trust centre states an aim of 99.99 per cent uptime, and the API Service Agreement gives no availability warranty, so no SLA (0). PDF Services is generally available, with structural extraction marked trial (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Security \u0026 auth, 40 out of 100, up to 10.5 more on the total\n\nWhy it scored 40: OAuth 2.0 client credentials per application, with a Bearer token of about 24 hours, no scopes and no refresh token. Secrets can be rotated and the docs forbid credentials in query parameters (20 of 30). No read-only mode. Sandbox mode is the only separation. The MCP server has no annotations or confirmation step, `delete_document` is permanent, `upload_document` reads any `file://` path, `download_document` writes to any absolute path, and the HTTP stream transport binds 0.0.0.0 by default with no authentication in the source (2 of 20). Extracted text, Markdown and HTML, and pages fetched by URL, are untrusted content with no injection guidance (0). The dashboard shows credits used and remaining. No per-call log is documented (4 of 15). A disclosure policy with safe harbour, CVE numbering authority status, security bulletins and SOC 2 Type II for the cloud PDF APIs, with an expired security.txt and no bounty (14 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 3. Agent ergonomics, 49 out of 100, up to 8.3 more on the total\n\nWhy it scored 49: The MCP server at 1.1.2 has 42 tools in about 89 KB of source with no toolsets, the more-than-30 band (5). The API returns a document ID, not the file, and takes page ranges, so responses stay small (15). We averaged the two to 10 because the listing covers both. Page ranges, extract types and image DPI limit output, and nothing lists or pages stored documents (12 of 20). Errors are JSON with a code and a message that names the valid values, and a failed task reports its error (14 of 20). Credits are deduplicated by a `request_id`, but no header for a client to set one is documented, and the MCP tools carry no `readOnlyHint` or `destructiveHint` (6 of 20). Most operations need only `documentId`. No official SDK package was found beyond the MCP server (7 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 4. Payments \u0026 pricing, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No x402, MPP or L402 (0). The price per unit is public without a login. One credit per successful request, at $1,750 a year for 5,000 credits or $4,500 for 15,000 (20). The Developer plan gives 500 credits a year and the sign-up page asks only for an email address. We did not go past that page, so a later card step is unchecked (20). A person signs up in a browser to get the client ID and secret (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 5. Schema \u0026 documentation, 62 out of 100, up to 6.2 more on the total\n\nWhy it scored 62: A public OpenAPI 3.1 file, version 2.3.0, describes 38 PDF Services operations, and the MCP server's tools carry typed zod schemas (25). No llms.txt on either portal host and no Markdown twins. The reference pages are drawn by script from the OpenAPI file (0). Operation descriptions state purpose, use cases and limits, and MCP descriptions give the upload, operate and poll order, but none says when not to use a tool (13 of 20). Enums cover compression levels, permissions, ciphers and rotations and required fields are marked, while page ranges are pattern-free strings (11 of 15). The PDF Services paths carry 235 examples and coded 400 and 500 bodies, but 401 and 429 are not declared on those operations (10 of 15). The file has a version number, paths are unversioned and no changelog was found (3 of 15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## 6. Maintenance \u0026 community, 38 out of 100, up to 5.4 more on the total\n\nWhy it scored 38: The MCP server's last npm release is 1.1.2 on 13 July 2026, 87 days before this check. The API itself has no dated release notes (20 of 30). One release in the last 90 days and no dated changelog entries (0). On GitHub, two bug reports of 27 August 2026 and a fix submitted on 29 August are still open, and the newest topics on the developer forum have no replies. Support runs through a case form (6 of 25). The server is in the official MCP registry under io.github.foxitsoftware, but the entry lists 0.2.3 from December 2025 (10 of 15). The repository has no CI workflow, no tests and no licence file, and its source stops at 0.2.3 while npm carries 1.1.2 (2 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Transparency \u0026 trust, 63 out of 100, up to 3.2 more on the total\n\nMade of editorial 44, provenance 81.\n\nWhy it scored 63: A closed service under a dated API Service Agreement (30 June 2025). The MCP server is MIT per package.json with no licence file (17 of 30). The agreement says uploaded documents are deleted within 30 days. The privacy policy says uploads are deleted when processing completes and outputs typically within a day, and it states an effective date of 10 May 2022. It says customer documents are not used to train AI models. No DPA was found (14 of 30). The agreement promises prior notice of changes with no period, and there is no deprecation policy (4 of 20). Server locations are named as the United States, Germany, Canada, Australia and Japan, the API host is a single na1 address, and no sub-processor list for the API was found (9 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Terms of service: read, states 5 of the 7 things a reader expects, and has 1 clause that costs points (6.3 of 10)\n- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)\n- Changelog: not found (0 of 10)\n- security.txt: published but past its Expires date (5 of 10)\n\n## What we couldn't check\n\nWhat 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.\n\n- The lead's docs link, docs.developer-api.foxit.com, is a Postman collection page. The current reference is at app.developer-api.foxit.com/reference and the API host is na1.fusion.foxit.com\n- The MCP server is a local package that calls the hosted API. No hosted MCP endpoint was found\n- The OpenAPI file's address was taken from the reference page's own configuration block, which also sets a YAML download. No other page links it\n- The official MCP server authenticates with `client_id` and `client_secret` headers, while the reference documents only a Bearer token from `/oauth/token`. Whether the header scheme stays supported is not stated\n- The PDF Services page claims ISO 27001. The trust centre and the API security page name SOC 2 Type II only\n- unchecked: whether the free plan asks for a card after the email step\n- unchecked: how a client sets the `request_id` that the credits guide says deduplicates retries\n- unchecked: whether a DPA or a sub-processor list for the APIs exists. None was linked from the pages read\n- unchecked: official SDK packages. A July 2025 forum post mentions a soft launch and none is linked from the reference\n- unchecked: the Postman documentation at docs.developer-api.foxit.com, which is drawn by script\n- The last few pages were fetched shortly after midnight on 9 October 2026 by the machine's clock. Dates here follow the batch date of 8 October\n\n## Weaknesses\n\n- OAuth client credentials carry no scopes, so every application credential can convert, delete and download\n- status.foxit.com has no component for the API gateway at na1.fusion.foxit.com or for PDF Services\n- No API changelog or deprecation policy found, and no llms.txt. The reference pages are drawn by script\n- MCP server 1.1.2 has 42 tools with no annotations, and its public repository still holds 0.2.3\n- The API agreement says uploads are deleted within 30 days. The privacy policy says on completion, with outputs kept about a day\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Exchange the client ID and secret at `https://na1.fusion.foxit.com/oauth/token` and cache the Bearer token. `expires_in` is about 24 hours and there is no refresh token\n- Upload first with `POST /pdf-services/api/documents/upload`, start the operation, poll `GET /pdf-services/api/tasks/{task-id}` until `COMPLETED`, then download `resultDocumentId`\n- Read the body of a 429. It means either the rate limit (15 a minute in sandbox, 100 in production) or `QUOTA_EXCEEDED` when credits run out\n- Keep uploads under 100 MB, and delete documents with `DELETE /pdf-services/api/documents/{document-id}` when done. Deletion is permanent\n- With the MCP server, pass only paths the task needs. `upload_document` reads any `file://` path and `download_document` writes to any absolute path\n\n## When it's done\n\nSend 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.\n",
    "grade": "D",
    "score": 48.3,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 47,
        "maxGain": 10.6,
        "reason": "Read with the hosted lines. status.foxit.com keeps 90-day component history for Foxit's cloud products, but has no component for the API gateway at na1.fusion.foxit.com or for PDF Services (8 of 20). With no component there is no readable incident history for this API (5). Rate limits are published as 15 requests a minute in sandbox mode and 100 in production mode, per application, over a rolling 60 seconds (15). The limits guide asks for exponential backoff on 429 and the credits guide says a retried request is not charged twice, but no Retry-After header is documented and 429 also signals an exhausted credit quota (9 of 15). The trust centre states an aim of 99.99 per cent uptime, and the API Service Agreement gives no availability warranty, so no SLA (0). PDF Services is generally available, with structural extraction marked trial (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 40,
        "maxGain": 10.5,
        "reason": "OAuth 2.0 client credentials per application, with a Bearer token of about 24 hours, no scopes and no refresh token. Secrets can be rotated and the docs forbid credentials in query parameters (20 of 30). No read-only mode. Sandbox mode is the only separation. The MCP server has no annotations or confirmation step, `delete_document` is permanent, `upload_document` reads any `file://` path, `download_document` writes to any absolute path, and the HTTP stream transport binds 0.0.0.0 by default with no authentication in the source (2 of 20). Extracted text, Markdown and HTML, and pages fetched by URL, are untrusted content with no injection guidance (0). The dashboard shows credits used and remaining. No per-call log is documented (4 of 15). A disclosure policy with safe harbour, CVE numbering authority status, security bulletins and SOC 2 Type II for the cloud PDF APIs, with an expired security.txt and no bounty (14 of 20).",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 49,
        "maxGain": 8.3,
        "reason": "The MCP server at 1.1.2 has 42 tools in about 89 KB of source with no toolsets, the more-than-30 band (5). The API returns a document ID, not the file, and takes page ranges, so responses stay small (15). We averaged the two to 10 because the listing covers both. Page ranges, extract types and image DPI limit output, and nothing lists or pages stored documents (12 of 20). Errors are JSON with a code and a message that names the valid values, and a failed task reports its error (14 of 20). Credits are deduplicated by a `request_id`, but no header for a client to set one is documented, and the MCP tools carry no `readOnlyHint` or `destructiveHint` (6 of 20). Most operations need only `documentId`. No official SDK package was found beyond the MCP server (7 of 15).",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 (0). The price per unit is public without a login. One credit per successful request, at $1,750 a year for 5,000 credits or $4,500 for 15,000 (20). The Developer plan gives 500 credits a year and the sign-up page asks only for an email address. We did not go past that page, so a later card step is unchecked (20). A person signs up in a browser to get the client ID and secret (0).",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 62,
        "maxGain": 6.2,
        "reason": "A public OpenAPI 3.1 file, version 2.3.0, describes 38 PDF Services operations, and the MCP server's tools carry typed zod schemas (25). No llms.txt on either portal host and no Markdown twins. The reference pages are drawn by script from the OpenAPI file (0). Operation descriptions state purpose, use cases and limits, and MCP descriptions give the upload, operate and poll order, but none says when not to use a tool (13 of 20). Enums cover compression levels, permissions, ciphers and rotations and required fields are marked, while page ranges are pattern-free strings (11 of 15). The PDF Services paths carry 235 examples and coded 400 and 500 bodies, but 401 and 429 are not declared on those operations (10 of 15). The file has a version number, paths are unversioned and no changelog was found (3 of 15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 38,
        "maxGain": 5.4,
        "reason": "The MCP server's last npm release is 1.1.2 on 13 July 2026, 87 days before this check. The API itself has no dated release notes (20 of 30). One release in the last 90 days and no dated changelog entries (0). On GitHub, two bug reports of 27 August 2026 and a fix submitted on 29 August are still open, and the newest topics on the developer forum have no replies. Support runs through a case form (6 of 25). The server is in the official MCP registry under io.github.foxitsoftware, but the entry lists 0.2.3 from December 2025 (10 of 15). The repository has no CI workflow, no tests and no licence file, and its source stops at 0.2.3 while npm carries 1.1.2 (2 of 10).",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 63,
        "maxGain": 3.2,
        "reason": "A closed service under a dated API Service Agreement (30 June 2025). The MCP server is MIT per package.json with no licence file (17 of 30). The agreement says uploaded documents are deleted within 30 days. The privacy policy says uploads are deleted when processing completes and outputs typically within a day, and it states an effective date of 10 May 2022. It says customer documents are not used to train AI models. No DPA was found (14 of 30). The agreement promises prior notice of changes with no period, and there is no deprecation policy (4 of 20). Server locations are named as the United States, Germany, Canada, Australia and Japan, the API host is a single na1 address, and no sub-processor list for the API was found (9 of 20).",
        "blend": "editorial 44, provenance 81",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "read, states 5 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 6.3,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 7 of the 8 things a reader expects",
        "points": 9.3,
        "max": 10
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "published but past its Expires date",
        "points": 5,
        "max": 10
      }
    ],
    "unchecked": [
      "The lead's docs link, docs.developer-api.foxit.com, is a Postman collection page. The current reference is at app.developer-api.foxit.com/reference and the API host is na1.fusion.foxit.com",
      "The MCP server is a local package that calls the hosted API. No hosted MCP endpoint was found",
      "The OpenAPI file's address was taken from the reference page's own configuration block, which also sets a YAML download. No other page links it",
      "The official MCP server authenticates with `client_id` and `client_secret` headers, while the reference documents only a Bearer token from `/oauth/token`. Whether the header scheme stays supported is not stated",
      "The PDF Services page claims ISO 27001. The trust centre and the API security page name SOC 2 Type II only",
      "unchecked: whether the free plan asks for a card after the email step",
      "unchecked: how a client sets the `request_id` that the credits guide says deduplicates retries",
      "unchecked: whether a DPA or a sub-processor list for the APIs exists. None was linked from the pages read",
      "unchecked: official SDK packages. A July 2025 forum post mentions a soft launch and none is linked from the reference",
      "unchecked: the Postman documentation at docs.developer-api.foxit.com, which is drawn by script",
      "The last few pages were fetched shortly after midnight on 9 October 2026 by the machine's clock. Dates here follow the batch date of 8 October"
    ],
    "weaknesses": [
      "OAuth client credentials carry no scopes, so every application credential can convert, delete and download",
      "status.foxit.com has no component for the API gateway at na1.fusion.foxit.com or for PDF Services",
      "No API changelog or deprecation policy found, and no llms.txt. The reference pages are drawn by script",
      "MCP server 1.1.2 has 42 tools with no annotations, and its public repository still holds 0.2.3",
      "The API agreement says uploads are deleted within 30 days. The privacy policy says on completion, with outputs kept about a day"
    ],
    "agentNotes": [
      "Exchange the client ID and secret at `https://na1.fusion.foxit.com/oauth/token` and cache the Bearer token. `expires_in` is about 24 hours and there is no refresh token",
      "Upload first with `POST /pdf-services/api/documents/upload`, start the operation, poll `GET /pdf-services/api/tasks/{task-id}` until `COMPLETED`, then download `resultDocumentId`",
      "Read the body of a 429. It means either the rate limit (15 a minute in sandbox, 100 in production) or `QUOTA_EXCEEDED` when credits run out",
      "Keep uploads under 100 MB, and delete documents with `DELETE /pdf-services/api/documents/{document-id}` when done. Deletion is permanent",
      "With the MCP server, pass only paths the task needs. `upload_document` reads any `file://` path and `download_document` writes to any absolute path"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-09",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}