# Magic Hour MCP vs Runway API (slim)

> Runway scores 59.2 (C) to Magic Hour MCP's 50.7 (D) for video generation. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/magic-hour-mcp-vs-runway.md (~4,350 tokens) · this version ~2,380 tokens · JSON https://www.anchorterminal.com/compare/magic-hour-mcp-vs-runway.json · canonical https://www.anchorterminal.com/compare/magic-hour-mcp-vs-runway
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Runway API scores 59.2 (C) on agent readiness against Magic Hour MCP's 50.7 (D), and leads in 5 of 7 scored categories. Magic Hour MCP leads on maintenance & community and transparency & trust. Both do video generation.

- Magic Hour MCP: D 50.7, rank #1053 of 1510 · https://www.anchorterminal.com/tools/magic-hour-mcp.min.md
- Runway API: C 59.2, rank #714 of 1510 · https://www.anchorterminal.com/tools/runway.min.md
- Magic Hour MCP, good for Agents making short-form video and images, from talking photos and ads to lip-synced translations, on a credit plan. Ahead on Maintenance & community, 75 against 62; Transparency & trust, 58 against 53. Also No incidents deducted, where Runway API loses 3 points for them.
- Runway API, good for Agents that want one key for Runway's own editing models (Aleph 2.0, Act-Two) and a menu of third-party models with one billing system. Ahead on Reliability, 67 against 35; Schema & documentation, 93 against 82; Agent ergonomics, 75 against 55; Security & auth, 51 against 45; Payments & pricing, 20 against 15.

| Category | Magic Hour MCP | Runway API |
| --- | --- | --- |
| Reliability (16%) | 35 | 67 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 82 | 93 |
| Agent ergonomics (13%) | 55 | 75 |
| Security & auth (14%) | 45 | 51 |
| Payments & pricing (10%) | 15 | 20 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 75 | 62 |
| Transparency & trust (7%) | 58 | 53 |

| Fact (where they differ) | Magic Hour MCP | Runway API |
| --- | --- | --- |
| Kind | MCP server | Model API |
| Vendor | Magic Hour AI, Inc. | Runway |
| Hosted endpoint | `https://mcp.magichour.ai/` | `https://api.dev.runwayml.com/v1` |
| Transports | Streamable HTTP | HTTP, Streamable HTTP |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Pay per use |
| Licence | none | Apache-2.0 (SDKs) |
| Tools exposed | 50 | none |
| MCP registry | `io.github.magichourhq/magic-hour` | not listed |
| Last release | none | 2026-10-28 |
| Terms last updated | not read yet | 2026-09-15 |
| Privacy policy last updated | not read yet | 2026-05-11 |
| Customer content may train models | not read yet | yes |
| Terms restrict automated access | not read yet | yes |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | yes |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | none | 20 stars, 56k npm/wk, 67k PyPI/wk |
| Agent reviews | none | 4/5 (2) |

Why the edge:
- Reliability, Runway API +32: 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.); Runway API 67 (Atlassian Statuspage at status.runwayml.com with a Public API component and history pages back to June 2026 (20). From 5 August to 3 November the history lists 11 incidents. On 17 October an unannounced "Scheduled Maintenance" filed as critical "affects all users" on App, Backend, Billing, Support and Public API from 18:55 UTC, with maintenance complete at 19:14 and the incident resolved at 21:18, a full outage of everything and so one major. The rest name one model (Aleph 2 on 29 September, Kling on 2 November, Magnific on 24 October) or say only "a problem affecting users", so they read as partial (10). The tiers page publishes per-model concurrency and a daily generation cap for each spend tier (15). Over the concurrency limit, tasks queue as THROTTLED instead of failing. The errors page says for each status whether a request may be retried (429, 502, 503 and 504 yes), with exponential backoff and jitter, and the SDKs retry on their own, with no idempotency key (12). No SLA published for self-serve tiers (0). The API and its models are generally available (10). 20+10+15+12+0+10 = 67.)
- Agent ergonomics, Runway API +20: 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.); Runway API 75 (Tasks are small JSON objects with output URLs, and the official SDKs include a wait-for-output helper, so an agent needn't write a polling loop (25). Ratio, duration and model choice set output size. No task list endpoint found (10). Failure codes separate moderation from other errors, so an agent knows when a retry is pointless (17). No idempotency key. The docs say not to retry SAFETY failures unchanged (10). Several required fields plus a mandatory version header, and official SDKs for Node and Python (13).)
- Maintenance & community, Magic Hour MCP +13: 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.); Runway API 62 (Model reading. Latest changelog entry on 28 October 2026 (Ideogram Vector), and 31 dated entries from 5 August to 28 October (30). Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 30 July 2026 with no earlier notice in the public changelog, and no later retirement notice was found (0). Busy dated changelog and a support desk (12). Official SDKs on npm and PyPI, Node 4.24.0 and Python 5.24.0 on 23 October 2026 (15). SDK repositories are public with CI and release workflows; pass state unread (5). 30+0+12+15+5 = 62.)
- Schema & documentation, Runway API +11: 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.); Runway API 93 (OpenAPI 3.1 at docs.dev.runwayml.com/openapi.json (25). llms.txt, llms-full.txt and a Markdown copy of every page (10). Model pages say what each model is for and which inputs it takes, though request fields differ from model to model (16). Typed fields with fixed ratios and duration ranges per model (13). Examples in curl, Node and Python, and failure codes such as SAFETY.* documented with what they mean (14). A dated X-Runway-Version header and a dated changelog with 23 entries between July and September 2026 (15).)
- Security & auth, Runway API +6: 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.); Runway API 51 (Model reading of the checklist (credential, training, retention, operator visibility, programme). One bearer key per project from the developer portal. The hosted MCP server uses OAuth. No permission scopes found on keys (20). Runway's data-security page doesn't say whether customer data trains models, and we found no statement in the API docs either (0). Output URLs expire within 24 to 48 hours (5), and Runway deletes customer data on request under its contracts (5). No input retention period found (0). Organisation workspace reporting for enterprise users since 28 July 2026, no per-call audit log found (8). No security.txt and no public disclosure policy (0). A private, invitation-only bug bounty (3). SOC 2 Type II and ISO/IEC 27001:2022 (5), with reports through a trust centre (5).)
- Payments & pricing, Runway API +5: Magic Hour MCP 15 (No machine payment protocol (0). Plan and credit-pack prices public, per-tool credit costs not read (10). 400 sign-up credits with no card, but API access sits on paid plans (5 of 20). A person signs up for a key in a browser (0). Tool discovery is open, but calls need a key (0). 0 + 10 + 5 + 0 = 15.); Runway API 20 (No x402, MPP or L402 (0). Per-second credit prices for every model are published at $0.01 a credit without a login, 12 credits a second for Gen-4.5 (20). No free generation credits, $10 minimum first purchase (0). A person signs up in the developer portal and buys credits (0).)