Kling AI API vs Magic Hour MCP

Kling AI API 15

No official OpenAPI. An independent profile on GitHub models the endpoints and says its schemas need checking against the live docs (0). kling.ai/llms.txt lists model IDs and per-second prices, but its links lead to pages that don't render without JavaScript, so half (5). llms.txt says what each model family is for, nothing more we could read (5). We couldn't read the parameter reference, so no typed inputs counted (0). No examples or error codes we could read (0). Versioned model IDs from kling-v1 to kling-v3. A release history page at kling.ai/release-note/release-history exists but renders only with JavaScript and its data request failed for us, so it isn't counted as a public changelog (5). The developer docs overview was tried again on 17 October and is still an app shell. 0+5+5+0+0+5 = 15.

Magic Hour MCP 82

All 50 tools read from tools/list with JSON Schema inputs and 29 enums, built from Magic Hour's OpenAPI specification (25). llms.txt (10). Long descriptions with a get_workflow_guide tool for choosing between them (17 of 20). Typed inputs with enums and no free-form objects (15). Worked examples; error responses not documented (5 of 15). Dated changelog with entries on 3 to 5 November 2026 (10 of 15, product changelog rather than MCP versions). 25 + 10 + 17 + 15 + 5 + 10 = 82.

Kling AI API 24

Model reading. The developer platform lists Kling 3.0 Turbo with a price and a "Kling 3.0 Turbo Now Available" banner on 17 October. Its API date of 17 June 2026 is from third-party coverage of the launch note, 122 days ago (10). Kling 4.0 has been in early access in the consumer app since 28 September, and Kling's blog of 15 October says the full model "launches this October". The developer platform lists no Kling 4.0 model on 17 October. Models from kling-v1 onward stay callable. No deprecation policy found, and Turbo and later models need newly generated keys, per the same launch note (10). No changelog we could read, support by email (4). No official SDK (0). Nothing to assess for package health (0). 10+10+4+0+0 = 24.

Magic Hour MCP 75

Changelog entries on 3, 4 and 5 November 2026 (30). More than three dated entries in 90 days (20). Changelog and support; issues on the public MCP repository not read (10 of 25). Registry entry io.github.magichourhq/magic-hour (0.1.1, 4 November) (15). No package health read (0). 30 + 20 + 10 + 15 + 0 = 75. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.

Kling AI API 27

Per the 1 October check, not re-read on 17 October, since the reference still renders only with JavaScript. Create calls return a task id to poll, per the request flow in llms.txt and the listing's checks. A third-party profile describes a callback_url, which we couldn't confirm on an official page (15). Mode (std or pro) and duration set output size, and we couldn't confirm a task list (10). No error reference we could read (0). No idempotency key or retry guidance found (0). No official SDK, and every call needs a JWT you sign yourself from an AccessKey and SecretKey (2). 15+10+0+0+2 = 27.

Magic Hour MCP 55

50 tools totalling about 160 KB of definitions (5). list_saved_items and project getters; limited size controls (10 of 20). Error handling not documented (5 of 20). Every tool annotated, 14 read-only and the three deletes marked destructive (20). Few required inputs and SDKs (Python, Node and others listed in the docs) (15). 5 + 10 + 5 + 20 + 15 = 55.

Kling AI API 20

Model reading of the checklist (credential, training, retention, operator visibility, programme). An AccessKey and SecretKey pair signs a short-lived JWT for each session, which keeps the secret off the wire, but we found no scopes and the secret key reaches everything, per the 1 October check (20). The Terms of Service, re-read on 17 October and still dated 21 April 2026, let Kling use Input to create, test, improve and train its models, and you can revoke that by email to support@kling.ai. They don't carve out API users, and the separate API paid-service terms render only with JavaScript, so we treat training as on by default (0). Data is kept as long as necessary for its purposes, with no period for API outputs (0). No audit log or per-call view found (0). security.txt returned 404 on kling.ai and klingai.com on 17 October, and no bug bounty or certification found (0). 20+0+0+0+0 = 20.

Magic Hour MCP 45

API keys as Bearer tokens or OAuth through the Claude and ChatGPT connectors (20 of 30). Destructive deletes are annotated; no read-only key (8 of 20). Tools return generated media, not third-party text (10). No audit log found (0). No security.txt or certifications found; face and voice tools come with policy limits in the terms (7 of 20). 20 + 8 + 10 + 0 + 7 = 45.

Kling AI API 15

No official status page. status.kling.ai and status.klingai.com still don't resolve on 17 October (0). No incident history to read (5). The developer pricing page, read on 17 October from the data embedded in the page, says the number of concurrent videos is set by the package and doesn't rise when more packages are bought, but gives no numbers. Third parties report 5 concurrent tasks on trial packages and 20 on standard ones, which we didn't count (0). No 429 or retry guidance we could read, per the 1 October check, not re-read on 17 October (0). No SLA found (0). Kling 3.0, 3.0 Omni and 3.0 Turbo are on the developer platform with no preview label (10). 0+5+0+0+0+10 = 15.

Magic Hour MCP 35

Status page at status.magichour.ai, all services online, with maintenance and previous incidents sections; no MCP component read (15). Incident history not read (5). No API rate limits found (0). No retry guidance found; wait_for_* tools poll long jobs (5 of 15). No SLA found (0). Not labelled beta (10). 15 + 5 + 0 + 5 + 0 + 10 = 35.

Kling AI API 46

Closed models. The Terms of Service (re-read on 17 October, still updated 21 April 2026, Singapore law, Kling AI Pte. Ltd. at One Raffles Place) are readable and say what Kling may do with your content, but the separate API paid-service terms render only with JavaScript (12 of 15). The privacy policy (also dated 21 April 2026) says data is stored on servers in Singapore and kept as long as necessary, and the terms add the training clause with an email opt-out. No DPA and no retention periods found (8 of 30). No deprecation policy or dated notices (0). Singapore storage and categories of service providers are disclosed, no named subprocessors (10). 12+8+0+10 = 30.

Magic Hour MCP 58

Closed service under terms naming Magic Hour AI, Inc., revised 3 October 2026 (15). The privacy policy says prompts, uploads and outputs aren't sold or used to train models, for free and paid accounts, and MCP requests are handled the same way; retention periods aren't given (20 of 30). No deprecation policy found (5 of 20). Subprocessors not read (10 of 20, model providers named in tool docs). 15 + 20 + 5 + 10 = 50.