{
  "fixes": {
    "slug": "liteapi",
    "name": "LiteAPI (Nuitee Connect)",
    "listing": "https://www.anchorterminal.com/tools/liteapi",
    "markdown": "# Fix list: LiteAPI (Nuitee Connect)\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/liteapi, the October 2026 research run, assessed 1 October 2026. Grade D, 53.5 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 LiteAPI (Nuitee Connect): 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. Security \u0026 auth, 33 out of 100, up to 11.7 more on the total\n\nWhy it scored 33: Plain `X-API-Key` keys, sandbox and production, with an HMAC signing scheme documented (20). The hosted MCP takes the key as `?apiKey=` in the URL as its documented setup, so we deduct 10. It also reads `X-Api-Key` or a Bearer header, which the docs don't lead with (10 of 30). Sandbox keys are the only reduced-privilege mode; the MCP's read-only and destructive annotations help a client ask before cancelling (8 of 20). Responses include guest reviews, hotel descriptions and AI-written answers from the beta `ask` endpoint, with no injection guidance (3 of 15). Advanced logs are a $4.99 a month dashboard add-on (10 of 15). The security overview names no certification, disclosure policy or bug bounty, and security.txt returned 404 on 30 September (2 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## 2. Reliability, 62 out of 100, up to 7.6 more on the total\n\nWhy it scored 62: Better Stack status page at status.liteapi.travel with six components (Dashboard, Whitelabel platform, Rates API, Hotel API, Hotel Booking Workflow, Flights Booking Workflow, the last marked not monitored) (20). Our reader saw no incident history on the page (5). Limits published with numbers, but they disagree. The rate-limiting page says 5 requests a second on sandbox keys and 250 in production (per the 30 September check), and the performance page says 500 a second per customer by default (12 of 15). 429 documented, with exponential backoff advised for transient errors, and `clientReference` works as an idempotency key on book and rebook (15). No SLA or availability target published (0). Core hotel endpoints are generally available; some data endpoints (semantic search, hotel Q and A, highlights, room search) are labelled beta (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## 3. 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). Per-unit prices published without login, updated 23 July 2026, core rates, prebook and book free within a reasonable look-to-book ratio, $0.05 per price-index call, $0.01 per places call, flight ticketing at 1 per cent (2 to 10 EUR) (20). Sandbox key at sign-up with no card (20). A person signs up in the dashboard (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## 4. Maintenance \u0026 community, 48 out of 100, up to 4.6 more on the total\n\nWhy it scored 48: The MCP repository's specs were updated on 11 September (booking and flights) and its docs on 30 September (30). No public changelog; the MCP repository has dated commits on 31 July, 21 August, 11 and 30 September but no releases (10 of 20). No public changelog for a closed service, and the MCP repository has 4 commits and 3 stars (5 of 15). The Node SDK (4.3.2) was last published in March 2025 and the other SDK repositories are older (3 of 15). The Node SDK repository carried an injected payload on main until April 2026 and has no CI, so we give nothing for package health (0).\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## 5. Transparency \u0026 trust, 48 out of 100, up to 4.6 more on the total\n\nMade of editorial 31, provenance 65.\n\nWhy it scored 48: Closed service under public terms naming Nuitée Travel Limited, Ireland. The MCP server is MIT and the Node SDK ISC (18 of 30). The privacy policy (20 May 2025) names the controller and says data is kept \"as long as necessary\", with no periods, no DPA and no named processors (10 of 30). No deprecation policy or dated notices found (0). Third parties described by function only (hosting, analytics, payments), with no list or data locations (3 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- Domain age: liteapi.travel, no registry record we could read (0 of 15)\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 6. Schema \u0026 documentation, 86 out of 100, up to 2.3 more on the total\n\nWhy it scored 86: OpenAPI 3 documents for 12 modules, linked from the docs and copied into the MCP repository (25). llms.txt with a Markdown twin for every docs page (10). Each operation opens with an overview that places it in the flow (\"Step 1 of 2 in the booking flow\") and says what it's for (18 of 20). Typed parameters with enums and required fields, and some free-form objects in analytics (13 of 15). An error-handling page and a separate list of booking-workflow error codes, with examples per operation (15). Version 3.0 in the path, but docs.liteapi.travel/changelog returns 404 and llms.txt links no changelog (5 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## 7. Agent ergonomics, 86 out of 100, up to 2.3 more on the total\n\nWhy it scored 86: Rates take `hotelIds`, `maxRatesPerHotel`, `includeHotelData`, `limit`, `offset` and `timeout`, so callers can size responses. The hosted MCP generates 111 tools from the specs with no toolsets, which is heavy for a model (20 of 25). Limit and offset on data endpoints and filters on rates (18 of 20). Booking-workflow error codes documented (20). `clientReference` as an idempotency key on book and rebook, and the MCP marks GET and rate searches read-only and DELETE and cancellation destructive (20). One request header for auth and few required fields. The Node SDK was last published in March 2025 and the Python, Go and Java repositories are older (8 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## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- -6, fixed 2026-04-20. The official Node SDK repository (liteapi-travel/nodejs-sdk) carried an obfuscated payload appended to index.js on main, introduced in a merge commit dated 8 July 2025 whose author and committer time zones differ, so the real injection date is unclear. Nuitée removed it in a commit titled \"remove obfuscated malware payload injected into index.js\" on 20 April 2026. The npm package 4.3.2 was published in March 2025, before it, so npm installs weren't affected; installs from the repository in that window were. A similar removal from test.js was merged in June 2025. We found no advisory or notice in the repository or docs. https://github.com/liteapi-travel/nodejs-sdk/commit/80d6d307fe3e82dc7bb448c3a8258e974f070ef7\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- Which rate limit applies, 250 a second (rate-limiting page) or 500 a second (performance page)\n- Whether Nuitée notified anyone who installed the Node SDK from GitHub between July 2025 and April 2026, and whether a GitHub security advisory exists (GitHub's API and issue pages were closed to us)\n- Whether the status page keeps incident history that our reader couldn't see\n- The listing's licence said MIT for the SDKs; the Node SDK is ISC, so we patched `license` and the SDK detail\n\n## Weaknesses\n\n- Hosted MCP's documented setup puts the API key in the URL query string and exposes 111 generated tools\n- Official Node SDK repository carried an injected payload on main until 20 April 2026, with no advisory found\n- No public changelog, deprecation policy or SLA\n- SDKs last published March 2025 or earlier\n- Rate limits differ between the rate-limiting page (250 a second) and the performance page (500 a second)\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- Use `/hotels/rates` with a short `hotelIds` list from `/data/hotels`; a broad rates call is slow and large\n- Always prebook before book and read the cancellation policy in the prebook response, since refundability differs per rate\n- Send a unique `clientReference` on book; a repeat returns error 4005 instead of a second booking\n- Set `margin` explicitly on every rates call. Zero means net rates with no commission to you\n- Send the key to the MCP in an `X-Api-Key` header rather than `?apiKey=` where the client allows it\n\n## What the review panel asked for\n\n- Production key steps\n- Header-first MCP setup\n- State the look-to-book ratio\n- Add MCP toolsets\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": 53.5,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 33,
        "maxGain": 11.7,
        "reason": "Plain `X-API-Key` keys, sandbox and production, with an HMAC signing scheme documented (20). The hosted MCP takes the key as `?apiKey=` in the URL as its documented setup, so we deduct 10. It also reads `X-Api-Key` or a Bearer header, which the docs don't lead with (10 of 30). Sandbox keys are the only reduced-privilege mode; the MCP's read-only and destructive annotations help a client ask before cancelling (8 of 20). Responses include guest reviews, hotel descriptions and AI-written answers from the beta `ask` endpoint, with no injection guidance (3 of 15). Advanced logs are a $4.99 a month dashboard add-on (10 of 15). The security overview names no certification, disclosure policy or bug bounty, and security.txt returned 404 on 30 September (2 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": "reliability",
        "name": "Reliability",
        "score": 62,
        "maxGain": 7.6,
        "reason": "Better Stack status page at status.liteapi.travel with six components (Dashboard, Whitelabel platform, Rates API, Hotel API, Hotel Booking Workflow, Flights Booking Workflow, the last marked not monitored) (20). Our reader saw no incident history on the page (5). Limits published with numbers, but they disagree. The rate-limiting page says 5 requests a second on sandbox keys and 250 in production (per the 30 September check), and the performance page says 500 a second per customer by default (12 of 15). 429 documented, with exponential backoff advised for transient errors, and `clientReference` works as an idempotency key on book and rebook (15). No SLA or availability target published (0). Core hotel endpoints are generally available; some data endpoints (semantic search, hotel Q and A, highlights, room search) are labelled beta (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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 (0). Per-unit prices published without login, updated 23 July 2026, core rates, prebook and book free within a reasonable look-to-book ratio, $0.05 per price-index call, $0.01 per places call, flight ticketing at 1 per cent (2 to 10 EUR) (20). Sandbox key at sign-up with no card (20). A person signs up in the dashboard (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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 48,
        "maxGain": 4.6,
        "reason": "The MCP repository's specs were updated on 11 September (booking and flights) and its docs on 30 September (30). No public changelog; the MCP repository has dated commits on 31 July, 21 August, 11 and 30 September but no releases (10 of 20). No public changelog for a closed service, and the MCP repository has 4 commits and 3 stars (5 of 15). The Node SDK (4.3.2) was last published in March 2025 and the other SDK repositories are older (3 of 15). The Node SDK repository carried an injected payload on main until April 2026 and has no CI, so we give nothing for package health (0).",
        "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": 48,
        "maxGain": 4.6,
        "reason": "Closed service under public terms naming Nuitée Travel Limited, Ireland. The MCP server is MIT and the Node SDK ISC (18 of 30). The privacy policy (20 May 2025) names the controller and says data is kept \"as long as necessary\", with no periods, no DPA and no named processors (10 of 30). No deprecation policy or dated notices found (0). Third parties described by function only (hosting, analytics, payments), with no list or data locations (3 of 20).",
        "blend": "editorial 31, provenance 65",
        "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"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 86,
        "maxGain": 2.3,
        "reason": "OpenAPI 3 documents for 12 modules, linked from the docs and copied into the MCP repository (25). llms.txt with a Markdown twin for every docs page (10). Each operation opens with an overview that places it in the flow (\"Step 1 of 2 in the booking flow\") and says what it's for (18 of 20). Typed parameters with enums and required fields, and some free-form objects in analytics (13 of 15). An error-handling page and a separate list of booking-workflow error codes, with examples per operation (15). Version 3.0 in the path, but docs.liteapi.travel/changelog returns 404 and llms.txt links no changelog (5 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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 86,
        "maxGain": 2.3,
        "reason": "Rates take `hotelIds`, `maxRatesPerHotel`, `includeHotelData`, `limit`, `offset` and `timeout`, so callers can size responses. The hosted MCP generates 111 tools from the specs with no toolsets, which is heavy for a model (20 of 25). Limit and offset on data endpoints and filters on rates (18 of 20). Booking-workflow error codes documented (20). `clientReference` as an idempotency key on book and rebook, and the MCP marks GET and rate searches read-only and DELETE and cancellation destructive (20). One request header for auth and few required fields. The Node SDK was last published in March 2025 and the Python, Go and Java repositories are older (8 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"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "liteapi.travel, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "-6, fixed 2026-04-20. The official Node SDK repository (liteapi-travel/nodejs-sdk) carried an obfuscated payload appended to index.js on main, introduced in a merge commit dated 8 July 2025 whose author and committer time zones differ, so the real injection date is unclear. Nuitée removed it in a commit titled \"remove obfuscated malware payload injected into index.js\" on 20 April 2026. The npm package 4.3.2 was published in March 2025, before it, so npm installs weren't affected; installs from the repository in that window were. A similar removal from test.js was merged in June 2025. We found no advisory or notice in the repository or docs. https://github.com/liteapi-travel/nodejs-sdk/commit/80d6d307fe3e82dc7bb448c3a8258e974f070ef7"
    ],
    "unchecked": [
      "Which rate limit applies, 250 a second (rate-limiting page) or 500 a second (performance page)",
      "Whether Nuitée notified anyone who installed the Node SDK from GitHub between July 2025 and April 2026, and whether a GitHub security advisory exists (GitHub's API and issue pages were closed to us)",
      "Whether the status page keeps incident history that our reader couldn't see",
      "The listing's licence said MIT for the SDKs; the Node SDK is ISC, so we patched `license` and the SDK detail"
    ],
    "weaknesses": [
      "Hosted MCP's documented setup puts the API key in the URL query string and exposes 111 generated tools",
      "Official Node SDK repository carried an injected payload on main until 20 April 2026, with no advisory found",
      "No public changelog, deprecation policy or SLA",
      "SDKs last published March 2025 or earlier",
      "Rate limits differ between the rate-limiting page (250 a second) and the performance page (500 a second)"
    ],
    "agentNotes": [
      "Use `/hotels/rates` with a short `hotelIds` list from `/data/hotels`; a broad rates call is slow and large",
      "Always prebook before book and read the cancellation policy in the prebook response, since refundability differs per rate",
      "Send a unique `clientReference` on book; a repeat returns error 4005 instead of a second booking",
      "Set `margin` explicitly on every rates call. Zero means net rates with no commission to you",
      "Send the key to the MCP in an `X-Api-Key` header rather than `?apiKey=` where the client allows it"
    ],
    "requests": [
      {
        "text": "Production key steps",
        "reviews": 1
      },
      {
        "text": "Header-first MCP setup",
        "reviews": 1
      },
      {
        "text": "State the look-to-book ratio",
        "reviews": 1
      },
      {
        "text": "Add MCP toolsets",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}