Magic Hour 远程 MCP 服务器是什么?

Magic Hour 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://mcp.magichour.ai/,AI 助手无需在本地安装或运行任何东西即可连接。

怎么连接 Magic Hour 的 MCP 服务器?

把端点 https://mcp.magichour.ai/ 添加到任意支持 MCP 的客户端,比如 Claude Code、Cursor 或 VS Code。本页的接入代码块可以一步配置好每个客户端。

Magic Hour 的 MCP 服务器需要认证吗?

需要。Magic Hour 使用 OAuth——第一次连接时,你的 MCP 客户端会打开浏览器窗口登录并授权,之后会复用这个凭证。

Magic Hour 的 MCP 服务器用的是哪种传输方式?

Magic Hour 暴露的是 streamable-http 端点,这是远程 MCP 服务器普遍使用、主流客户端都支持的传输方式。

Magic Hour MCP Server：工具、安装与配置

Read Magic Hour workflow guidance for face swap, image editing, image-to-video, video generation, lip sync, UGC ads, talking photos or API integration. Returns product and documentation URLs, exact tool names, ordered steps, example requests, follow-up edits and review criteria; does not generate media, spend credits or check account access.

Check that the Magic Hour MCP server is reachable.

Poll a video project until it completes, errors, is canceled, or times out. After a timeout, resume with the same id; do not create another generation. Returns sanitized download fields. Use `exact_download_urls[n]` or `downloads[n].url` exactly as returned; do not shorten it, remove query parameters, or append expiration metadata. Inline previews share an 8 MiB limit; all download URLs remain available.

Poll an image project until it completes, errors, is canceled, or times out. After a timeout, resume with the same id; do not create another generation. Returns the final project JSON and, when complete, attempts to inline image downloads for Inspector or compatible clients. Returns sanitized download fields. Use `exact_download_urls[n]` or `downloads[n].url` exactly as returned; do not shorten it, remove query parameters, or append expiration metadata. Inline previews share an 8 MiB limit; all download URLs remain available.

Poll an audio project until it completes, errors, is canceled, or times out. After a timeout, resume with the same id; do not create another generation. Returns the final project JSON and, when complete, attempts to inline audio downloads for Inspector or compatible clients. Returns sanitized download fields. Use `exact_download_urls[n]` or `downloads[n].url` exactly as returned; do not shorten it, remove query parameters, or append expiration metadata. Inline previews share an 8 MiB limit; all download URLs remain available.

Fetch a image `downloads[n].url` from a completed image project and return it as inline MCP image content for compatible clients. Pass the exact full signed URL from `downloads[n].url` without trimming query parameters; `expires_at` is separate metadata, not part of the URL. Inline media is capped at 8 MiB; use the signed URL directly for larger downloads.

Fetch a audio `downloads[n].url` from a completed audio project and return it as inline MCP audio content for compatible clients. Pass the exact full signed URL from `downloads[n].url` without trimming query parameters; `expires_at` is separate metadata, not part of the URL. Inline media is capped at 8 MiB; use the signed URL directly for larger downloads.

Fetch a video `downloads[n].url` from a completed video project and return it as an embedded MCP binary resource for compatible clients. Pass the exact full signed URL from `downloads[n].url` without trimming query parameters; `expires_at` is separate metadata, not part of the URL. Inline media is capped at 8 MiB; use the signed URL directly for larger downloads.

Get the current credit balance and subscription details of the account that owns the API key.

Returns active saved items owned by the authenticated account, newest first. Each item includes every saved asset with a durable file_path for reuse in compatible generation APIs and a temporary signed URL for previewing or downloading. Filter by type to find characters, references, voices, moodboards, or brand kits. To fetch the next page, pass the response's next_cursor as cursor.

MCP guidance: - This only creates presigned upload URLs. For local files, upload the raw bytes to each returned `upload_url` outside the generation call, then pass the matching `file_path` into the create tool. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Generates a list of pre-signed upload URLs for the assets required. This API is only necessary if you want to upload to Magic Hour's storage. Refer to the [Input Files Guide](https://docs.magichour.ai/integration/inputs-and-outputs) for more details. The response array will match the order of items in the request body. **Valid file extensions per asset type**: - video: mp4, m4v, mov, webm - audio: mp3, wav, aac, flac, webm, weba, m4a, opus, ogg, oga, aiff, amr - image: png, jpg, jpeg, jfif, heic, heif, webp, avif, jp2, tiff, tif, bmp - gif: gif, webp, webm > Note: `gif` is only supported for face swap API `video_file_path` field. Once you receive an upload URL, send a `PUT` request to upload the file directly. Example: ``` curl -X PUT --data '@/path/to/file/video.mp4' \ https://videos.magichour.ai/api-assets/id/video.mp4?<auth params from the API response> ```

Get the details of a face detection task. Use this API to get the list of faces detected in the image or video to use in the [face swap photo](https://docs.magichour.ai/api-reference/image-projects/face-swap-photo) or [face swap video](https://docs.magichour.ai/api-reference/video-projects/face-swap-video) API calls for multi-face swaps.

MCP guidance: - This starts an async face-detection task and returns an `id`. Use the face-detection details endpoint with that id to retrieve detected faces before doing individual face swaps. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Detect faces in an image or video. Use this API to get the list of faces detected in the image or video to use in the [face swap photo](https://docs.magichour.ai/api-reference/image-projects/face-swap-photo) or [face swap video](https://docs.magichour.ai/api-reference/video-projects/face-swap-video) API calls for multi-face swaps. Note: Face detection is free to use for the near future. Pricing may change in the future.

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. 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

Permanently delete the rendered video. This action is not reversible, please be sure before deleting.

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Requires a still portrait in `assets.image_file_path` and an existing recording in `assets.audio_file_path`, plus `start_seconds` and `end_seconds`. Text alone is not accepted; this tool does not synthesize speech. For existing video plus replacement audio, use `lip_sync_create_video` instead.

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a spoken UGC video from a prepared image and script. Returns a project ID; poll GET /v1/video-projects/{id} for status and downloads. To compose an image, generate the image separately with the Image Editor API and supply its download URL.

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Video Editor you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding video editor into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a video editor job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: output size and plan requirements vary by workflow and model. Some workflows derive output size from the input video. - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are charged when the job is queued (`credits_charged` in the response). Tools billed per frame charge an estimate and settle to the frames that actually render once the job finishes; tools billed per second charge the final amount upfront. Failed jobs are refunded. For detailed examples, see the [product page](https://magichour.ai/products/ai-video-editor).

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Video Translator you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding video translator into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a video translator job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: output size and plan requirements vary by workflow and model. Some workflows derive output size from the input video. - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are charged when the job is queued (`credits_charged` in the response). Tools billed per frame charge an estimate and settle to the frames that actually render once the job finishes; tools billed per second charge the final amount upfront. Failed jobs are refunded. For detailed examples, see the [product page](https://magichour.ai/products/ai-video-translator).

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Video Upscaler you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding video upscaler into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a video upscaler job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: output size and plan requirements vary by workflow and model. Some workflows derive output size from the input video. - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are charged when the job is queued (`credits_charged` in the response). Tools billed per frame charge an estimate and settle to the frames that actually render once the job finishes; tools billed per second charge the final amount upfront. Failed jobs are refunded. For detailed examples, see the [product page](https://magichour.ai/products/video-upscaler).

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a Animation video. The estimated frame cost is calculated based on the `fps` and `end_seconds` input.

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. **What this API does** Create the same Audio To Video you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow. **Good for** - Automation and batch processing - Adding audio to video into apps, pipelines, or tools **How it works (3 steps)** 1) Upload your inputs (video, image, or audio) with [Generate Upload URLs](https://docs.magichour.ai/api-reference/files/generate-asset-upload-urls) and copy the `file_path`. 2) Send a request to create a audio to video job with the basic fields. 3) Check the job status until it's `complete`, then download the result from `downloads`. **Key options** - Inputs: usually a file, sometimes a YouTube link, depending on project type - Resolution: output size and plan requirements vary by workflow and model. Some workflows derive output size from the input video. - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are charged when the job is queued (`credits_charged` in the response). Tools billed per frame charge an estimate and settle to the frames that actually render once the job finishes; tools billed per second charge the final amount upfront. Failed jobs are refunded. For detailed examples, see the [product page](https://magichour.ai/products/audio-to-video).

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Automatically generate subtitles for your video in multiple languages.

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Replace a video subject or transfer video motion onto a reference character image. Requires `assets.video_file_path`, `assets.image_file_path` and `end_seconds`. Model support controls duration, resolution and subject selection; see parameter schemas. Generation consumes credits; the queued video charge is an estimate, with the final charge available on the completed project.

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Requires `start_seconds`, `end_seconds` and `assets.video_source` with its matching `assets.video_file_path` or `assets.youtube_url`. Use `assets.image_file_path` for all-faces mode, or `assets.face_mappings` for individual-faces mode after face detection. Generation consumes credits; the queued video charge is an estimate, with the final charge available on the completed project.

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Animate a supplied product photo, portrait or scene. Requires `assets.image_file_path` and `end_seconds`. Use the approved image directly; edit only for a requested visual change or a source problem that prevents the shot. Prompt for motion while preserving the supplied appearance. Model, duration, resolution and audio support vary. Generation consumes credits; the queued video charge is an estimate, with the final charge available on the completed project.

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Match existing video to replacement audio. Requires `assets.audio_file_path`, `assets.video_source` and its matching `assets.video_file_path` or `assets.youtube_url`, plus `start_seconds` and `end_seconds`. For a still portrait plus audio, use `ai_talking_photo_create_talking_photo`. Text alone is not an audio input. Generation consumes credits; the queued video charge is an estimate, with the final charge available on the completed project.

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Generate a new scene from `style.prompt` and `end_seconds` when no supplied starting image is required. To animate an approved product photo or portrait, use `image_to_video_create_video` instead.

MCP guidance: - Starts an async video job; returns `id` and `credits_charged`. For finished results, call `wait_for_video_project` with that id or poll `GET /v1/video-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Restyle an existing video segment with an art-style preset or a custom prompt. Requires `assets.video_source` with its matching `assets.video_file_path` or `assets.youtube_url`, `start_seconds`, `end_seconds` and `style.art_style`. For a custom prompt, set `style.prompt_type` to `custom` or `append_default` and provide `style.prompt`; with `default`, the supplied prompt is ignored. This API supports v1/v2 presets, not v3. Generation consumes credits; the queued video charge is an estimate, with the final charge available on the completed project.

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. Check the progress of a image 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

Permanently delete the rendered image(s). This action is not reversible, please be sure before deleting.

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Change outfits in photos in seconds with just a photo reference. Each photo costs 25 credits.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Edit facial features of an image using AI. Each edit costs 1 frame. The height/width of the output image depends on your subscription. Please refer to our [pricing](https://magichour.ai/pricing) page for more details

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI GIF. Each GIF costs 50 credits.

MCP guidance: - Requires one or more source images in `assets.image_file_paths`. For prompt-only creation, use `ai_image_generator_create_image` instead. - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Edit supplied images using `assets.image_file_paths` and `style.prompt`. For prompt-only creation use `ai_image_generator_create_image`. Editing is not a required preparation step before image-to-video when the approved source already meets the brief. Check model eligibility: the omitted/default model is not universally available on Free.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create an AI headshot. Each headshot costs 50 credits.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI image with advanced model selection and quality controls.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Upscale your image using AI. Each 2x upscale costs 50 credits for balanced/creative modes, and 25 credits for preserve. 4x upscale costs 200 and 100 credits respectively.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI generated meme. Each meme costs 10 credits.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Create an AI QR code. Each QR code costs 0 credits.

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Swap a person into a scene image using Nano Banana 2 Lite (640px/1k) or Nano Banana 2 (2k/4k). Credits depend on `resolution` (from 50 credits at 640px upward).

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Create a face swap photo. Each photo costs 10 credits. The height/width of the output image depends on your subscription. Please refer to our [pricing](https://magichour.ai/pricing) page for more details

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors. MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Swap a head onto a body image. Each image costs 10 credits. Output resolution depends on your subscription; you may set `max_resolution` lower than your plan maximum if desired.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Remove background from image. Each image costs 5 credits.

MCP guidance: - Starts an async image job; returns `id` and `credits_charged`. For finished results, call `wait_for_image_project` with that id or poll `GET /v1/image-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. - For `*_file_path`, use an existing Magic Hour path or the upload-URL endpoint's `file_path` after uploading raw bytes to its presigned URL. Direct public media URLs may work if stable and fetchable as raw bytes; hotlinked URLs can fail. Prefer the upload-URL endpoint when unsure. Colorize image. Each image costs 10 credits.

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. Check the progress of a audio 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

Permanently delete the rendered audio file(s). This action is not reversible, please be sure before deleting.

MCP guidance: - Starts an async audio job; returns `id` and `credits_charged`. For finished results, call `wait_for_audio_project` with that id or poll `GET /v1/audio-projects/{id}` until `complete`, `error`, or `canceled`. Results include `downloads`; wait helpers add `exact_download_urls`. Preserve signed URLs and query parameters; never append expiration metadata. Generate music from a description, with optional custom lyrics or instrumental-only output. Costs 1 credits per requested second. Returns a project ID; poll GET /v1/audio-projects/{id} for status and downloads.

Magic Hour MCP Server已验证已精选

关于 Magic Hour MCP Server

连接信息

接入方式