Magic Hour

by io.github.magichourhq

Overview Discussions Admin

video_projects_retrieve_details

Check the progress of a video project. The downloads field is populated after a successful render.

Statuses

queued — waiting to start
rendering — in progress
complete — ready; see downloads
error — a failure occurred (see error)
canceled — user canceled
draft — not used

MCP guidance:

Use this after a create tool to poll job status. When status is complete, surface the downloads URLs to the user; if status is error, surface the error message.
Each downloads[n].url is already the full signed download URL. Use it exactly as returned. Do not shorten it, strip query parameters, or append expires_at onto the URL string.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes	Unique ID of the video project. This value is returned by all of the POST APIs that create a video.
`context`	No	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Unique ID of the video. Use it with the [Get video Project API](https://docs.magichour.ai/api-reference/video-projects/get-video-details) to fetch status and downloads.
`fps`	Yes	Frame rate of the video. If the status is not 'complete', the frame rate is an estimate and will be adjusted when the video completes.
`name`	Yes	The name of the video.
`type`	Yes	The type of the video project. Possible values are ANIMATION, AUTO_SUBTITLE, VIDEO_TO_VIDEO, FACE_SWAP, TEXT_TO_VIDEO, IMAGE_TO_VIDEO, LIP_SYNC, TALKING_PHOTO, AVATAR, VIDEO_UPSCALER, VIDEO_EDITOR, CHARACTER_REPLACE, VIDEO_COLORIZER, VIDEO_COLOR_GRADER, VIDEO_TRANSLATOR, MUSIC_VIDEO, EXTEND, AUDIO_TO_VIDEO, VIDEO_EXPANDER, UGC_AD
`error`	Yes	In the case of an error, this object will contain the error encountered during video render
`width`	Yes	The width of the final output video. A value of -1 indicates the width can be ignored.
`height`	Yes	The height of the final output video. A value of -1 indicates the height can be ignored.
`status`	Yes	The status of the video. - `draft` - the project was created but has not been submitted for rendering - `queued` - the job is waiting for an available server - `rendering` - the job is being processed; the `video.started` webhook event fires when rendering begins - `complete` - the job finished successfully; fires `video.completed` - `error` - the job failed during processing; fires `video.errored` - `canceled` - the job was manually canceled (for example from the Magic Hour web app) Note: `rendering`, `complete`, and `error` have matching webhook events; `canceled` does not - a canceled job emits no webhook event, so poll this endpoint to detect cancellation.
`enabled`	Yes	Whether this resource is active. If false, it is deleted.
`downloads`	Yes
`created_at`	Yes
`end_seconds`	Yes	End time of your clip (seconds). Must be greater than start_seconds.
`start_seconds`	Yes	Start time of your clip (seconds). Must be ≥ 0.
`credits_charged`	Yes	The amount of credits deducted from your account to generate the video. If the status is not 'complete', this value is an estimate and may be adjusted upon completion based on the actual FPS of the output video. If video generation fails, credits will be refunded, and this field will be updated to include the refund.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 11, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

Changed1 schema field changedSep 5, 2026

changedOutput schema / properties / type / description

Previous value: -"The type of the video project. Possible values are ANIMATION, AUTO_SUBTITLE, VIDEO_TO_VIDEO, FACE_SWAP, TEXT_TO_VIDEO, IMAGE_TO_VIDEO, LIP_SYNC, TALKING_PHOTO, AVATAR, VIDEO_UPSCALER, VIDEO_EDITOR, CHARACTER_REPLACE, VIDEO_COLORIZER, VIDEO_TRANSLATOR, MUSIC_VIDEO, EXTEND, AUDIO_TO_VIDEO, VIDEO_EXPANDER, UGC_AD"New value: +"The type of the video project. Possible values are ANIMATION, AUTO_SUBTITLE, VIDEO_TO_VIDEO, FACE_SWAP, TEXT_TO_VIDEO, IMAGE_TO_VIDEO, LIP_SYNC, TALKING_PHOTO, AVATAR, VIDEO_UPSCALER, VIDEO_EDITOR, CHARACTER_REPLACE, VIDEO_COLORIZER, VIDEO_COLOR_GRADER, VIDEO_TRANSLATOR, MUSIC_VIDEO, EXTEND, AUDIO_TO_VIDEO, VIDEO_EXPANDER, UGC_AD"

First observedSep 1, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does a good job: it discloses that `downloads` is only populated after a successful render, defines every status value, and warns that URLs are pre-signed and must be used verbatim. It omits auth/permission requirements and any rate-limit or polling-cadence guidance, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded one-line purpose, then a scannable status bullet list, then operational guidance. Every line contributes; the status enum and the URL-handling warning are both information an agent actually needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be re-explained, and the description still adds the status vocabulary and the signed-URL handling rule. For a simple two-parameter polling tool this is fully sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters are documented in the schema, so the baseline is 3. The description adds no extra meaning about `id` or `context` beyond what the schema already states, though it does explain output semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Check the progress of a video project') and enumerates the status states the tool reports, which is more informative than a restatement. It does not, however, explicitly differentiate itself from the sibling wait_for_video_project or fetch_video_download, which an agent must disambiguate against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'MCP guidance' block gives a clear trigger ('Use this after a create tool to poll job status') plus explicit follow-up actions for the complete and error cases. It stops short of naming the alternative (wait_for_video_project) or stating when polling is preferable to a blocking wait, so it is clear context rather than full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Magic Hour tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.