HiruAI Creative Cloud
REMOTE · MCP.HIRUAI.COM
Generate images, voice, music and video, then edit them into a finished movie from one plan.
Available components
Last scanned (23 hours ago)
Scores higher than 60% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Design and Media
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 Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability46
- 21% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 9314 tokens (~206/item across 45 items; 34 tools + 11 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 Management3
- Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 34 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 36 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
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 21 Nov 26 −2
- Schema quality: 265 → 206 ▲ functional
- Stability: unverified → 0.03 ▲ functional
- Schema quality: unverified → 21 ▲ functional
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 20 Nov 26 +38
- Transport: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. security
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- First check of Tool coverage: 100 functional
- 14 Nov 26 38
First indexed and scored.
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 21 Nov 2026 · Probed https://mcp.hiruai.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.hiruai.com | CN=YR2,O=Let's Encrypt,C=US | 8 Nov 2026 | 6 Feb 2027 | RSA 2048 | SHA256-RSA | 54cec2661f8223600daaaa5289be98d2588 |
| SANs: mcp.hiruai.com | ||||||
| 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.hiruai.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| hiruai.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://mcp.hiruai.com/.well-known/oauth-protected-resource"
Bearer resource_metadata="https://mcp.hiruai.com/.well-known/oauth-protected-resource" | Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'self'; script-src 'self'; style-src 'self'; img-src 'self' blob: data:; media-src 'self' blob:; connect-src 'self'; font-src 'self'; frame-ancestors 'none'; base-uri 'none'; form-action 'self' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | no-referrer |
Protected resource metadata
| Document | https://mcp.hiruai.com/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://mcp.hiruai.com/mcp |
| Authorisation server | https://mcp.hiruai.com |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.hiruai.com/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.hiruai.com/mcp | HTTPS enforced | 308 | https://mcp.hiruai.com/mcp |
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 →
asset_upload Upload file to private library ~188
Upload a local image, audio or video as base64 to the private 30-day file library; returns an upload asset ID immediately without a GPU job. Use this ID in uploads for Video/Edit/Upscale/Voice, or as a Movie asset. Reuse idempotency_key on retries. Never put base64 or a local path in batch arguments.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Confirm the user has permission to process any personal data in the inputs. |
| acknowledge_rights | boolean | yes | Confirm the user has the rights or permissions to use the source material. |
| base64 | string | yes | Source file bytes encoded as base64. |
| filename | string | yes | Filename for the source upload. |
| idempotency_key | string | yes | Unique key for the intended operation. Reuse it on network retries. |
| mime_type | string | yes | Media type of the uploaded file. |
No output schema declared.
No examples provided.
assets_list List my assets ~23
List your reusable image, video, voice, music and sound effect assets.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
batch_control Pause, resume or cancel plan ~65
Pause future dispatch, resume, or cancel remaining steps on explicit user request. Already submitted work finishes safely and remains visible.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Pause future dispatch, resume the plan, or cancel the remaining steps. |
| batch_id | string | yes | UUID of the production plan. |
No output schema declared.
No examples provided.
batch_get Get production plan ~39
Read one plan, steps and results when requested. Prefer handing off its URL after submission.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | UUID of the production plan. |
No output schema declared.
No examples provided.
batch_repair Repair failed plan step ~146
On user request, replace arguments of a definitively rejected failed step that has no accepted request ID. Supply expected_arguments from batch_get to prevent stale edits. Revalidates the entire plan, preserves completed work, and pauses; use batch_control resume after repair. Never use for uncertain or accepted jobs.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge | boolean | yes | Confirm the user authorized repairing this failed step. |
| arguments | object | yes | Complete replacement arguments for the failed step. |
| batch_id | string | yes | UUID of the production plan. |
| expected_arguments | object | yes | Current step arguments from batch_get, used to detect concurrent edits. |
| step_key | string | yes | Key of the failed step to repair. |
No output schema declared.
No examples provided.
batch_submit Submit production plan ~285
Save the entire plan once and immediately hand the returned dashboard URL to the user. Do NOT poll or wait for completion. Server handles dependencies, GPU waits, studio/email locks and quota retries. Default start=false lets the user review and start on the dashboard. start=true requires user authorization for automatic execution and every acknowledgement. A submitted plan continues after the chat closes or session expires. Send the same dopamine_hooks you validated; they are recorded in goal for the user to review.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_execution | boolean | – | Confirm the user explicitly approved starting the production plan automatically. |
| dopamine_hooks | array | – | Creative baseline: the dopamine hook(s) you built into the FINAL work. Declare at least one for any plan that creates image, voice, music, video or movie output, after reading dopamine_hooks_get. The… |
| goal | string | yes | Desired finished deliverable and user-provided requirements. |
| idempotency_key | string | yes | Unique key for the intended operation. Reuse it on network retries. |
| start | boolean | – | Start after submission when authorized; false saves a draft for review. |
| steps | array | yes | Production steps in dependency order, with studio arguments and result bindings. |
| title | string | yes | Display title for the plan or movie. |
No output schema declared.
No examples provided.
batch_validate Validate production plan ~186
Validate a dependency-ordered plan without starting jobs or consuming studio quota. Read capabilities_get first. Declare the dopamine hook(s) built into the final work as dopamine_hooks; a creative plan without one stays valid and returns a dopamine_hook_missing suggestion; explicit user overrides are allowed.
| Name | Type | Req | Description |
|---|---|---|---|
| dopamine_hooks | array | – | Creative baseline: the dopamine hook(s) you built into the FINAL work. Declare at least one for any plan that creates image, voice, music, video or movie output, after reading dopamine_hooks_get. The… |
| goal | string | yes | Desired finished deliverable and user-provided requirements. |
| steps | array | yes | Production steps in dependency order, with studio arguments and result bindings. |
| title | string | yes | Display title for the plan or movie. |
No output schema declared.
No examples provided.
batches_list List production plans ~26
List plans owned by this account when the user asks; do not use a polling loop.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
blender_program_validate Validate Blender program ~274
Validate a Blender bpy Python program, output contract and CPU limits without execution or GPU jobs. Read blender_programming from capabilities_get. Owned assets are checked by movie_plan_validate.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | – | Confirm the user has permission to process any personal data in the inputs. |
| acknowledge_rights | boolean | – | Confirm the user has the rights or permissions to use the source material. |
| aspect | string | – | Aspect ratio category for the movie output. |
| audio_layers | array | – | Optional audio tracks for voice, music and sound effects, with timing and gain. |
| blender_program | – | – | Optional Blender scene or timeline edit with its assets and output settings. |
| clips | array | – | Ordered visual clips with their durations, sources and optional trims. |
| duration | – | – | Target movie duration in seconds. |
| graphics | array | – | Timed on-screen elements such as titles and captions. |
| music | – | – | Optional background music track with placement on the movie timeline. |
| sync_plan | – | – | Submit before Voice finishes. Bind a future voice asset; the server reads its output timing and resolves sentence/scene placement automatically after completion. |
| title | string | – | Display title for the plan or movie. |
| version | integer | – | Movie timeline schema version. |
| voice | – | – | Optional narration track with placement on the movie timeline. |
No output schema declared.
No examples provided.
capabilities_get Read capabilities ~84
Read live studio input schemas, supported outputs and planning rules before making a plan. Optional service returns only that studio and relevant details; omit it for the existing full catalog. Start with workflow_get for task routing. Creative hooks are a nudge, not a rejection rule.
| Name | Type | Req | Description |
|---|---|---|---|
| service | string | – | Studio that owns the source, or whose details or requests you want to read. |
No output schema declared.
No examples provided.
dopamine_hooks_get Read dopamine hooks ~119
Read the creative baseline catalog: everyday situations in which people feel reward and anticipation (dopamine hooks), each with visual, audio and situation cues and guardrails, plus the planning principle and this week's practice theme. Call before planning any creative work, then build at least one hook into the final output and declare it in batch_validate/batch_submit. Filter with group or ids. No generation, quota or GPU job.
| Name | Type | Req | Description |
|---|---|---|---|
| group | string | – | Filter hooks to one catalog group. |
| ids | array | – | Filter hooks to the specified catalog IDs. |
No output schema declared.
No examples provided.
edit_create Edit image ~485
Submit edit work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. For quality-first image generation or editing, prefer the connected agent’s own image tool when it supports the requested operation, for example ChatGPT image generation and image editing. Check what this client actually exposes, including in Claude. Honor the user’s chosen provider. For anime-style character illustration, HiruAI Image offers WAI Illustrious SDXL v17 when available in image_models_get.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_rights | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_safety | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| files | array | – | Optional upload parts (max 20 MiB total). Use audio for Voice, file for Edit/Upscale, image_upload/last_image_upload/voice_upload/music_upload for Video. |
| generated_request_id | array | – | 1–3 owned completed request UUIDs, aligned by index with services and variants. Use bindings for future step outputs. |
| generated_service | array | – | One service per selected image; omission defaults every image to image. When supplied, length must match generated_request_id and generated_variant. |
| generated_variant | array | – | Variants aligned by index: image base/nsfw; edit result; upscale upscaled/4k. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| instruction | string | yes | Editing instruction, 3–2000 characters after whitespace normalization. |
| source_type | string | yes | Choose upload for file inputs or generated for owned HiruAI results. Do not mix both kinds. |
| uploads | array | – | Private uploaded file references from asset_upload or the web file library. No local paths, URLs or base64 in plans. Set the corresponding source/image/voice/music mode to upload. |
No output schema declared.
No examples provided.
image_create Create image ~586
Submit image work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. Creative baseline: unless the user declined, build at least one dopamine hook from dopamine_hooks_get into this prompt, script or sound. First call image_models_get. Present dated original-model Arena scores (not scores of our quantized/LoRA recipes), traits, availability and native alternatives to help the user choose. Select one model; never invent agreement or substitute user consent for the operator's hosting permission. For quality-first image generation or editing, prefer the connected agent’s own image tool when it supports the requested operation, for example ChatGPT image generation and image editing. Check what this client actually exposes, including in Claude. Honor the user’s chosen provider. For anime-style character illustration, HiruAI Image offers WAI Illustrious SDXL v17 when available in image_models_get.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_adult | boolean | – | Confirm that the requesting user meets the adult-use requirement. |
| acknowledge_model_terms | boolean | – | Use true only after actual user authorization for the selected model. User consent never grants the platform hosting rights. |
| acknowledge_no_real_person | boolean | – | Confirm the prompt and inputs do not depict or imitate a real person for adult content. |
| acknowledge_noncommercial | boolean | – | Use true only after actual user authorization for the selected model. User consent never grants the platform hosting rights. |
| acknowledge_nsfw_policy | boolean | – | Confirm the user accepts the selected model’s adult-content restrictions. |
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_rights | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| model | string | – | One model per new request; Qwen Image 2512 Q4 + Lightning (8-step) is the default. The separate 50-step quality model remains selectable. Read image_models_get first and present dated quality evidenc… |
| model_terms_version | string | – | Current catalog version from image_models_get, required with creator model terms. |
| nsfw_requested | boolean | – | Legacy alias selecting only Z-Image Turbo NSFW. Prefer model; never request two models together. |
| prompt | string | yes | Image prompt, 3–2000 characters. Whitespace is collapsed before backend length/safety checks. |
No output schema declared.
No examples provided.
image_models_get Compare image models ~69
Read the same image-model catalog as image.hiruai.com: current execution availability, traits, dated Arena evidence, model-specific consent and ChatGPT/Claude native-image alternatives. Show the relevant comparison to the user before selecting a model. This read-only call creates no job and consumes no generation quota.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
media_create Analyze public video ~214
Submit media work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_rights | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| source_url | string | yes | Single YouTube/Shorts/Live/TikTok video HTTPS URL,10–2048 characters. No playlists, credentials or non-443 ports. The backend validates allowed hosts and paths. |
| title | string|null | – | Optional request title, up to200 characters. |
No output schema declared.
No examples provided.
media_library_clip Cut clip from library item ~265
Cut a frame-accurate H.264/AAC clip (max 180 s, location metadata removed) from a library item and, by default, save it to the 30-day upload library. The returned upload asset_id can be used directly in Video uploads or as a Movie clip (service=upload). Only for reuse_policy=reusable items unless the user confirms they hold the rights.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm_reference_rights | boolean | – | Required true to cut a reference_only item; the user must state they hold permission. |
| end_seconds | number | yes | Clip end offset in seconds from the beginning of the source. |
| idempotency_key | string | yes | Unique key for the intended operation. Reuse it on network retries. |
| include_audio | boolean | – | Include the source audio in the clip when available. |
| item_id | string | yes | UUID of the media library item. |
| max_height | integer | – | Maximum height in pixels for the clipped output. |
| rendition | string | – | Select the master or proxy as the source, or let the server choose. |
| save_as_asset | boolean | – | Save the clip to the private upload library for reuse in subsequent jobs. |
| start_seconds | number | yes | Clip start offset in seconds from the beginning of the source. |
No output schema declared.
No examples provided.
media_library_get Get media library item ~186
Read one library item's AI-ready manifest (schema hiruai.media-library.v1): provenance and reuse guidance, renditions, catalog (summary, chapters, reusable_segments, voice_reference_candidates, generation_prompts, sensitive flags), scenes with spoken text and OCR. Book-mode items also include book_pages (ordered OCR, observed printed_page, source timestamp/frame, confidence and warnings) and book_analysis coverage limits. Never infer missing pages or treat OCR scores as verified accuracy. include_transcript adds every timed transcript segment. Respect reuse_policy: "reusable" footage (own/licensed) may be cut into new work; "reference_only" third-party media is for analysis, structure and style reference only, never copied into an output.
| Name | Type | Req | Description |
|---|---|---|---|
| include_transcript | boolean | – | Include every timed transcript segment in the manifest. |
| item_id | string | yes | UUID of the media library item. |
No output schema declared.
No examples provided.
media_library_list List media library ~165
List the account's media library (own recordings and referenced YouTube/TikTok/Instagram Reels/web videos) with status, tags, summary and reuse_policy. Respect reuse_policy: "reusable" footage (own/licensed) may be cut into new work; "reference_only" third-party media is for analysis, structure and style reference only, never copied into an output.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of entries or matches to return. |
| origin | string | – | Filter to a source platform or the user’s own recording. |
| query | string | – | Search text for matching media library entries or moments. |
| reuse_policy | string | – | Filter by the library’s recorded footage reuse policy. |
| tag | string | – | Filter entries by their saved tag. |
No output schema declared.
No examples provided.
media_library_search Search media library ~206
Find moments across the library by speech, on-screen text, book-page text or visual similarity (multilingual CLIP). OCR includes book pages; book_page searches only book text and observed printed page labels. Returns item_id, start/end seconds, matched text, page_index (zero-based observation, not printed folio), printed_page and keyframe paths when available. Use for production planning and to pick clip ranges. Respect reuse_policy: "reusable" footage (own/licensed) may be cut into new work; "reference_only" third-party media is for analysis, structure and style reference only, never copied into an output.
| Name | Type | Req | Description |
|---|---|---|---|
| kinds | array | – | Choose which indexes to search: speech, OCR, visuals or book-page text. |
| limit | integer | – | Maximum number of entries or matches to return. |
| query | string | yes | Search text for matching media library entries or moments. |
| reuse_policy | string | – | Filter by the library’s recorded footage reuse policy. |
No output schema declared.
No examples provided.
movie_asset_metadata Inspect audio asset ~81
Inspect actual audio duration, bounded waveform and imported subtitle cues without generation or GPU jobs.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | UUID of the source asset. |
| service | string | yes | Studio that owns the source, or whose details or requests you want to read. |
| variant | string | – | Named output variant to read; available variants depend on the studio and request. |
No output schema declared.
No examples provided.
movie_asset_timing_set Save audio timing ~61
Save verified source timestamps for owned audio. Times are original-file seconds, not movie offsets. Never invent alignment from transcript length.
| Name | Type | Req | Description |
|---|---|---|---|
| asset | – | yes | Owned source audio asset to update. |
| timing | – | yes | Verified cues in source-file seconds and their provenance. |
No output schema declared.
No examples provided.
movie_create Compose movie ~348
Submit movie work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. Creative baseline: unless the user declined, build at least one dopamine hook from dopamine_hooks_get into this prompt, script or sound.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | – | Confirm the user has permission to process any personal data in the inputs. |
| acknowledge_rights | boolean | – | Confirm the user has the rights or permissions to use the source material. |
| aspect | string | – | Aspect ratio category for the movie output. |
| audio_layers | array | – | Optional audio tracks for voice, music and sound effects, with timing and gain. |
| blender_program | – | – | Optional Blender scene or timeline edit with its assets and output settings. |
| clips | array | – | Ordered visual clips with their durations, sources and optional trims. |
| duration | – | – | Target movie duration in seconds. |
| graphics | array | – | Timed on-screen elements such as titles and captions. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| music | – | – | Optional background music track with placement on the movie timeline. |
| sync_plan | – | – | Submit before Voice finishes. Bind a future voice asset; the server reads its output timing and resolves sentence/scene placement automatically after completion. |
| title | string | – | Display title for the plan or movie. |
| version | integer | – | Movie timeline schema version. |
| voice | – | – | Optional narration track with placement on the movie timeline. |
No output schema declared.
No examples provided.
movie_plan_validate Validate movie edit ~273
Validate an edit against owned real source durations, mapped narration cues and layer limits. No render, email, quota or GPU job. Use after capabilities_get and before submission.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | – | Confirm the user has permission to process any personal data in the inputs. |
| acknowledge_rights | boolean | – | Confirm the user has the rights or permissions to use the source material. |
| aspect | string | – | Aspect ratio category for the movie output. |
| audio_layers | array | – | Optional audio tracks for voice, music and sound effects, with timing and gain. |
| blender_program | – | – | Optional Blender scene or timeline edit with its assets and output settings. |
| clips | array | – | Ordered visual clips with their durations, sources and optional trims. |
| duration | – | – | Target movie duration in seconds. |
| graphics | array | – | Timed on-screen elements such as titles and captions. |
| music | – | – | Optional background music track with placement on the movie timeline. |
| sync_plan | – | – | Submit before Voice finishes. Bind a future voice asset; the server reads its output timing and resolves sentence/scene placement automatically after completion. |
| title | string | – | Display title for the plan or movie. |
| version | integer | – | Movie timeline schema version. |
| voice | – | – | Optional narration track with placement on the movie timeline. |
No output schema declared.
No examples provided.
movie_script_analyze Analyze narration script ~62
Get stable sentence IDs from the exact planned Voice text BEFORE generation. Use these IDs in sync_plan.segments so a final edit plan can be submitted now and resolved automatically when narration completes.
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | Exact narration text planned for the Voice request. |
No output schema declared.
No examples provided.
music_create Create music ~455
Submit music work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. Creative baseline: unless the user declined, build at least one dopamine hook from dopamine_hooks_get into this prompt, script or sound.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_rights | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_safety | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| bpm | integer | – | Integer tempo from30 through300 BPM; default120. |
| description | string | yes | Music description, 3–2000 characters after trim and newline normalization. Do not include unsupported control characters. |
| duration_seconds | integer | – | Exactly one of 10,15,30,60,120 seconds; default30. A 15-second ad can request15. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| instrumental | boolean | – | Set true for instrumental BGM and omit lyrics. Defaults false, which requires lyrics. |
| key_scale | string | – | Case-sensitive note plus Major or Minor. Sharps are supported; flat spellings are not accepted. |
| language | string | – | Lyrics language code; unlike Voice, Music uses short codes such as ko. |
| lyrics | string | – | Lyrics up to 4096 characters. Required and non-empty for instrumental=false; omit or send an empty string for instrumental=true. |
| time_signature | string | – | API meter code: "2", "3", "4", or "6" only. For 4/4 time submit "4". Never send "4/4", "3/4" or "6/8" in this field; musical wording may appear in description. |
No output schema declared.
No examples provided.
request_get Get request status ~54
Read request status, progress, results and analysis text.
| Name | Type | Req | Description |
|---|---|---|---|
| request_id | string | yes | UUID of the studio request. |
| service | string | yes | Studio that owns the source, or whose details or requests you want to read. |
No output schema declared.
No examples provided.
requests_list List studio requests ~37
List work history for one studio.
| Name | Type | Req | Description |
|---|---|---|---|
| service | string | yes | Studio that owns the source, or whose details or requests you want to read. |
No output schema declared.
No examples provided.
result_read Read result file ~109
Read a completed output in base64 chunks (up to 1 MiB). Follow next_offset until null. Binary files remain private.
| Name | Type | Req | Description |
|---|---|---|---|
| offset | integer | – | Byte offset for the next result chunk, starting at zero. |
| request_id | string | yes | UUID of the studio request. |
| service | string | yes | Studio that owns the source, or whose details or requests you want to read. |
| variant | string | – | Named output variant to read; available variants depend on the studio and request. |
No output schema declared.
No examples provided.
sfx_create Generate sound effects ~357
Submit sfx work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. Creative baseline: unless the user declined, build at least one dopamine hook from dopamine_hooks_get into this prompt, script or sound. HiruAI has recorded provider acceptance of Stable Audio and Gemma terms for hosted SFX. Omit legacy acknowledge_model_terms; do not ask for a separate end-user model-terms confirmation. Rights, privacy and safety acknowledgements and model use restrictions remain in force.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_model_terms | boolean | – | Optional legacy user acknowledgement. HiruAI has recorded provider acceptance of Stable Audio and Gemma terms for this hosted SFX service (2026-11-19-hiruai-sa3-gemma-provider-v1). Omit this field; d… |
| acknowledge_privacy | boolean | yes | Confirm the user has permission to process any personal data in the inputs. |
| acknowledge_rights | boolean | yes | Confirm the user has the rights or permissions to use the source material. |
| acknowledge_safety | boolean | yes | Confirm the user accepts the safety restrictions for this request. |
| description | string | yes | Describe the sound effect to generate, including audible events and timing. |
| duration_seconds | integer | – | Requested sound effect duration in seconds. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| seed | – | – | Optional random seed for the sound effect. |
No output schema declared.
No examples provided.
upscale_create Upscale image ~361
Submit upscale work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_rights | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| files | array | – | Optional upload parts (max 20 MiB total). Use audio for Voice, file for Edit/Upscale, image_upload/last_image_upload/voice_upload/music_upload for Video. |
| generated_request_id | string|null | – | Owned completed source request UUID; required with source_type=generated. |
| generated_service | string|null | – | For generated input: image or edit. Omission defaults to image. |
| generated_variant | string|null | – | For generated input: image uses base/nsfw; edit uses result. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| source_type | string | yes | Choose an uploaded source or a previous generated image. |
| source_url | string|null | – | For source_type=url only: a public HTTPS image URL, max 2048 characters; no credentials, IP literals, non-443 ports or private network destinations. |
| uploads | array | – | Private uploaded file references from asset_upload or the web file library. No local paths, URLs or base64 in plans. Set the corresponding source/image/voice/music mode to upload. |
No output schema declared.
No examples provided.
video_create Create video clip ~825
Submit video work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. Creative baseline: unless the user declined, build at least one dopamine hook from dopamine_hooks_get into this prompt, script or sound.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_rights | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_safety | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| files | array | – | Optional upload parts (max 20 MiB total). Use audio for Voice, file for Edit/Upscale, image_upload/last_image_upload/voice_upload/music_upload for Video. |
| height | integer | yes | Allowed pairs: 1920×1088,1088×1920,1024×1024. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| image_mode | string | – | Choose how the first image is supplied. |
| image_request_id | string|null | – | Required for library mode: owned completed request UUID, or bind a prior output ID. |
| image_service | string|null | – | Required for library mode: image, edit or upscale. |
| image_variant | string|null | – | Required for library mode: image base/nsfw, edit result, upscale upscaled/4k. |
| last_image_mode | string | – | Choose how the final image is supplied. |
| last_image_request_id | string|null | – | Required for library mode: owned completed request UUID, or bind a prior output ID. |
| last_image_service | string|null | – | Required for library mode: image, edit or upscale. |
| last_image_variant | string|null | – | Required for library mode: image base/nsfw, edit result, upscale upscaled/4k. |
| music_mode | string | – | Choose how optional background music is supplied. |
| music_request_id | string|null | – | Required for library mode: owned completed music request UUID. |
| num_frames | integer | yes | 24fps frame count; about 2/3/4/5 seconds. |
| prompt | string | yes | Motion/scene prompt, 3–2000 characters after trim and newline normalization; unsupported control characters are rejected. |
| reference_mode | string | – | keyframes=RGB endpoint guidance. depth/canny/pose=full-video IC-LoRA control; inspect video_reference_capabilities first, unavailable modes fail without submitting a job. |
| reference_movie_id | string|null | – | Completed owned Blender reference Movie ID. Bind the preceding movie step output id here. |
| reference_strength | number | – | Set the strength of the full-video conditioning reference. |
| uploads | array | – | Private uploaded file references from asset_upload or the web file library. No local paths, URLs or base64 in plans. Set the corresponding source/image/voice/music mode to upload. |
| voice_fit | string | – | Voice longer than the clip's audio window ((num_frames-1)/24 s, 2-5 s): trim keeps only the first window (published default); reject refuses before any request/quota so a full-preservation intent nev… |
| voice_mode | string | – | Choose how an optional narration track is supplied. |
| voice_request_id | string|null | – | Required for library mode: owned completed voice request UUID. |
| width | integer | yes | Allowed pairs: 1920×1088,1088×1920,1024×1024. |
No output schema declared.
No examples provided.
video_reference_capabilities Read video reference support ~42
Read the deployed Video reference paths and GPU validation status. Distinguishes endpoint keyframes from full-video depth/canny/pose IC-LoRA. No generation.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
voice_create Create voice ~518
Submit voice work for the authenticated account. Returns an asynchronous request ID. For a sequence of work, prefer batch_submit and hand off the dashboard URL without polling. Use library IDs from assets_list where supported. Rights/privacy acknowledgements must reflect the user’s authorization; never invent consent. Limits remain active through result email delivery. Creative baseline: unless the user declined, build at least one dopamine hook from dopamine_hooks_get into this prompt, script or sound.
| Name | Type | Req | Description |
|---|---|---|---|
| acknowledge_privacy | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_safety | boolean | yes | Must be true only when the user has authorized the stated rights, privacy or safety acknowledgement. Never invent consent. |
| acknowledge_voice_rights | boolean | – | Must be true in base mode after user authorization to reproduce the voice; never invent the speaker consent. |
| files | array | – | Optional upload parts (max 20 MiB total). Use audio for Voice, file for Edit/Upscale, image_upload/last_image_upload/voice_upload/music_upload for Video. |
| idempotency_key | string | yes | Unique per intended operation. Reuse on network retries. |
| instruction | string | – | Voice/tone instructions up to 1000 characters. design requires at least 3 characters; custom optionally accepts instructions; base forbids them. |
| language | string | – | Use the full case-sensitive language name, e.g. Korean, not ko. |
| mode | string | yes | base requires reference audio + exact transcript + voice rights. custom uses a named speaker; design uses instruction. |
| reference_text | string | – | Exact transcript of the reference audio, 1–4000 characters in base mode. Leave empty/omit in custom/design. |
| reference_voice_id | string | – | Base clone only: owned completed Voice result, or bind a preceding Voice output id. Mutually exclusive with uploads/inline audio. The server uses the source text as the exact reference transcript; om… |
| speaker | string | – | Required in custom mode. Leave empty/omit in base and design. Names are case-sensitive. |
| text | string | yes | Text to speak, 1–2000 characters after trim and line-ending normalization. |
| uploads | array | – | Private uploaded file references from asset_upload or the web file library. No local paths, URLs or base64 in plans. Set the corresponding source/image/voice/music mode to upload. |
No output schema declared.
No examples provided.
workflow_get Read workflow and recipes ~100
Start here: read the HiruAI workflow without installing skills. Get task-specific steps, consent and publishing guidance, recovery actions, or a full recipe with recipe_id even if this client cannot read MCP resources. Read-only; no job or quota.
| Name | Type | Req | Description |
|---|---|---|---|
| recipe_id | string | – | Optionally include the full selected recipe, including for clients without resources/read. |
| topic | string | – | Read only the topic needed now; omitted means the first-use workflow. |
No output schema declared.
No examples provided.
How do I install the HiruAI Creative Cloud MCP server?
HiruAI Creative Cloud is a hosted endpoint at https://mcp.hiruai.com/mcp, 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.hiruai.com
claude mcp add --transport http com-hiruai-creative-cloud 'https://mcp.hiruai.com/mcp'
What is the HiruAI Creative Cloud MCP server?
HiruAI Creative Cloud is an MCP server listed in the public MCP registry as com.hiruai/creative-cloud. Generate images, voice, music and video, then edit them into a finished movie from one plan. This page covers its hosted endpoint (https://mcp.hiruai.com/mcp).
Is the HiruAI Creative Cloud MCP server safe to use?
HiruAI Creative Cloud scores 74 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 HiruAI Creative Cloud MCP server expose?
HiruAI Creative Cloud exposes 34 tools: image_create, edit_create, upscale_create, voice_create, music_create, and 29 more. Their descriptions and schemas cost roughly 7,294 tokens of context every time the server is loaded.
Does the HiruAI Creative Cloud MCP server require authentication?
Yes. HiruAI Creative Cloud asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the HiruAI Creative Cloud MCP server still maintained?
HiruAI Creative Cloud is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the HiruAI Creative Cloud MCP server?
VerifyMCP ran 13 checks on HiruAI Creative Cloud, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.