Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Magic Hour

REMOTE · MCP.MAGICHOUR.AI · SCANNED SEP 20

Create and edit images, videos, and audio through Magic Hour's hosted Streamable HTTP MCP server.

Available components

+3 this week 73 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability70
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 25080 tokens (~545/item across 46 items; 45 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management64
  • Stability check failed: schema churn in the 20 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions. See how to fix → Fail
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 84% of tool parameters carry a description.Partial
  • Structured output schemas are declared (80% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "video_projects_delete" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 47 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
Install

How do I install the Magic Hour MCP server?

Magic Hour is a hosted endpoint at https://mcp.magichour.ai/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.magichour.ai

# add to Claude Code
claude mcp add --transport http magichourhq-magic-hour 'https://mcp.magichour.ai/'
// .cursor/mcp.json
{
  "mcpServers": {
    "magichourhq-magic-hour": {
      "url": "https://mcp.magichour.ai/"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "magichourhq-magic-hour": {
      "type": "http",
      "url": "https://mcp.magichour.ai/"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.magichourhq-magic-hour]
url = "https://mcp.magichour.ai/"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "magichourhq-magic-hour": {
      "type": "remote",
      "url": "https://mcp.magichour.ai/",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add magichourhq-magic-hour --url 'https://mcp.magichour.ai/' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  magichourhq-magic-hour:
    url: "https://mcp.magichour.ai/"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "magichourhq-magic-hour": {
      "Transport": "http",
      "Url": "https://mcp.magichour.ai/"
    }
  }
}
# add to Vellum
assistant mcp add magichourhq-magic-hour -t streamable-http -u 'https://mcp.magichour.ai/'
// mcp.json
{
  "mcpServers": {
    "magichourhq-magic-hour": {
      "type": "http",
      "url": "https://mcp.magichour.ai/"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 61 to 64.

  • 19 Sept 26 0
    • New tool “saved_items_list” functional
    • “image_to_video_create_video” reworded the description of “audio” cosmetic
    • “image_to_video_create_video” reworded the description of “end_seconds” cosmetic
    • “image_to_video_create_video” reworded the description of “model” cosmetic
    • “image_to_video_create_video” reworded the description of “resolution” cosmetic
    • “text_to_video_create_video” reworded the description of “aspect_ratio” cosmetic
    • “text_to_video_create_video” reworded the description of “audio” cosmetic
    • “text_to_video_create_video” reworded the description of “end_seconds” cosmetic
    • “text_to_video_create_video” reworded the description of “model” cosmetic
    • “text_to_video_create_video” reworded the description of “resolution” cosmetic
  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 54 to 57.

  • 17 Sept 26 0
    • “ai_image_editor_create_image” reworded the description of “model” cosmetic
    • “ai_image_editor_create_image” reworded the description of “resolution” cosmetic
    • “ai_image_generator_create_image” reworded the description of “model” cosmetic
    • “ai_image_generator_create_image” reworded the description of “resolution” cosmetic

    4 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 51.

  • 13 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
  • 12 Sept 26 0
    • Schema quality: 406 → 540 functional
    • Tool coverage: 79% → 84% functional
    • “account_retrieve” added an optional parameter “context” cosmetic
    • “ai_clothes_changer_create_image” added an optional parameter “context” cosmetic
    • “ai_face_editor_edit_image” added an optional parameter “context” cosmetic
    • “ai_gif_generator_create_image” added an optional parameter “context” cosmetic
    • “ai_headshot_generator_create_image” added an optional parameter “context” cosmetic
    • “ai_image_editor_create_image” added an optional parameter “context” cosmetic
    • “ai_image_generator_create_image” added an optional parameter “context” cosmetic
    • “ai_image_upscaler_create_image” added an optional parameter “context” cosmetic
    • “ai_meme_generator_create_image” added an optional parameter “context” cosmetic
    • “ai_qr_code_generator_create_image” added an optional parameter “context” cosmetic
    • “ai_talking_photo_create_talking_photo” added an optional parameter “context” cosmetic
    • “ai_video_editor_create_video” added an optional parameter “context” cosmetic
    • “ai_voice_cloner_create_audio” added an optional parameter “context” cosmetic
    • “ai_voice_generator_create_audio” added an optional parameter “context” cosmetic
    • “animation_create_video” added an optional parameter “context” cosmetic
    • “audio_projects_delete” added an optional parameter “context” cosmetic
    • “audio_projects_retrieve_details” added an optional parameter “context” cosmetic
    • “audio_to_video_create_video” added an optional parameter “context” cosmetic
    • “auto_subtitle_generator_create_video” added an optional parameter “context” cosmetic
    • “body_swap_create_image” added an optional parameter “context” cosmetic
    • “character_replace_create_video” added an optional parameter “context” cosmetic
    • “face_detection_detect_faces” added an optional parameter “context” cosmetic
    • “face_detection_retrieve_details” added an optional parameter “context” cosmetic
    • “face_swap_create_video” added an optional parameter “context” cosmetic
    • “face_swap_photo_create_image” added an optional parameter “context” cosmetic
    • “fetch_audio_download” added an optional parameter “context” cosmetic
    • “fetch_image_download” added an optional parameter “context” cosmetic
    • “fetch_video_download” added an optional parameter “context” cosmetic
    • “head_swap_create_image” added an optional parameter “context” cosmetic
    • “image_background_remover_create_image” added an optional parameter “context” cosmetic
    • “image_projects_delete” added an optional parameter “context” cosmetic
    • “image_projects_retrieve_details” added an optional parameter “context” cosmetic
    • “image_to_video_create_video” added an optional parameter “context” cosmetic
    • “lip_sync_create_video” added an optional parameter “context” cosmetic
    • “photo_colorizer_create_image” added an optional parameter “context” cosmetic
    • “ping” added an optional parameter “context” cosmetic
    • “text_to_video_create_video” added an optional parameter “context” cosmetic
    • “video_assets_generate_presigned_url” added an optional parameter “context” cosmetic
    • “video_projects_delete” added an optional parameter “context” cosmetic
    • “video_projects_retrieve_details” added an optional parameter “context” cosmetic
    • “video_to_video_create_video” added an optional parameter “context” cosmetic
    • “wait_for_audio_project” added an optional parameter “context” cosmetic
    • “wait_for_image_project” added an optional parameter “context” cosmetic
    • “wait_for_video_project” added an optional parameter “context” cosmetic
    • “ai_image_editor_create_image” reworded the description of “model” cosmetic
    • “ai_image_editor_create_image” reworded the description of “resolution” cosmetic
    • “ai_image_generator_create_image” reworded the description of “model” cosmetic
    • “ai_image_generator_create_image” reworded the description of “resolution” cosmetic
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 31 to 34.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://mcp.magichour.ai/

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.magichour.ai CN=YR2,O=Let's Encrypt,C=US 15 Sept 2026 14 Dec 2026 RSA 2048 SHA256-RSA 6aa235fe3d5f0055b5768ea1fcbdd2d8535
SANs: mcp.magichour.ai
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.magichour.ai. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
magichour.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.magichour.ai/ Verified 200
http (plaintext) http://mcp.magichour.ai/ HTTPS enforced 308 https://mcp.magichour.ai/
MCP tools · 45 exposed · ~24,788 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
video_to_video_create_video ~780

**What this API does** Create the same Video 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 video 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 video 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: free users are limited to 576px; higher plans unlock HD and larger sizes - Extra fields: e.g. `face_swap_mode`, `start_seconds`/`end_seconds`, or a text prompt **Cost** Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done. For detailed examples, see the [product page](https://magichour.ai/products/video-to-video). MCP guidance: - This starts an async video generation job and returns `id` plus `credits_charged` immediately. If the user wants the finished result, call the `wait_for_video_project` helper with the returned id, or poll the matching `GET /v1/video-projects/{id}` endpoint until status is `complete`, `error`, or `canceled`. Completed projects include `downloads` with direct URLs. The custom wait helper also returns `exact_download_urls` separately from expiration metadata. - For `*_file_path` values, prefer an existing Magic Hour file path or a `file_path` returned by the upload-URL endpoint after the file bytes are uploaded. Direct public media URLs may work when they are stable, fetchable, and return raw file bytes, but hotlinked URLs can fail; when in doubt, use the presigned upload flow…

NameTypeReqDescription
assetsobjectyesProvide the assets for video-to-video. For video, The `video_source` field determines whether `video_file_path` or `youtube_url` field is used
contextstringExplain 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,…
end_secondsnumberyesEnd time of your clip (seconds). Must be greater than start_seconds.
fps_resolutionstringDetermines whether the resulting video will have the same frame per second as the original video, or half. * `FULL` - the result video will have the same FPS as the input video * `HALF` - the result…
namestringGive your video a custom name for easy identification.
start_secondsnumberyesStart time of your clip (seconds). Must be ≥ 0.
styleobjectyes
NameTypeReqDescription
credits_chargedintegeryesThe 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 o…
idstringyesUnique 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.

No examples provided.

wait_for_audio_project ~273

Poll an audio project until it completes, errors, is canceled, or times out. 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.

NameTypeReqDescription
contextstringExplain 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,…
idstringyes
include_inline_downloadsboolean
max_bytes_per_downloadinteger
max_inline_downloadsinteger
poll_interval_secondsnumber
timeout_secondsnumber

No output schema declared.

No examples provided.

wait_for_image_project ~273

Poll an image project until it completes, errors, is canceled, or times out. 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.

NameTypeReqDescription
contextstringExplain 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,…
idstringyes
include_inline_downloadsboolean
max_bytes_per_downloadinteger
max_inline_downloadsinteger
poll_interval_secondsnumber
timeout_secondsnumber

No output schema declared.

No examples provided.

wait_for_video_project ~242

Poll a video project until it completes, errors, is canceled, or times out. 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.

NameTypeReqDescription
contextstringExplain 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,…
idstringyes
include_inline_downloadsboolean
max_inline_downloadsinteger
poll_interval_secondsnumber
timeout_secondsnumber

No output schema declared.

No examples provided.

Common questions

What is the Magic Hour MCP server?

Magic Hour is an MCP server listed in the public MCP registry as io.github.magichourhq/magic-hour. Create and edit images, videos, and audio through Magic Hour's hosted Streamable HTTP MCP server. This page covers its hosted endpoint (https://mcp.magichour.ai/).

Is the Magic Hour MCP server safe to use?

Magic Hour scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Magic Hour MCP server expose?

Magic Hour exposes 45 tools: ping, wait_for_video_project, wait_for_image_project, wait_for_audio_project, fetch_image_download, and 40 more. Their descriptions and schemas cost roughly 24,788 tokens of context every time the server is loaded.

Does the Magic Hour MCP server require authentication?

No. We connected to Magic Hour without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Magic Hour MCP server still maintained?

Magic Hour is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.