Skip to content

HiruAI Creative Cloud MCP server

com.hiruai/creative-cloudhiruai.comstreamable-httpv1.3.2Scanned

Generate images, voice, music and video, then edit them into a finished movie from one plan.

34 tools: 1 can delete or cancel things, 17 change things and 16 only read.

Tools: 1 delete, 0 irreversible, 17 write, 16 read.
  • Reads private data · 1
  • Reads text others write · 3
  • Can send data out · 0
  • 9 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the HiruAI Creative Cloud MCP server can do

The HiruAI Creative Cloud MCP server is published by hiruai.com, a domain the MCP Registry verified. It has 34 tools. It can delete or cancel things (1 tool: batch_control) and create or change data (17 tools: image_create, edit_create, upscale_create, voice_create and 13 more). 16 tools only read.

1 tool reads private data (image_models_get); 3 tools bring in text other people can write (media_create, image_models_get and media_library_list).

The fixed checks matched 9 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.3.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

34 tools

Deletes or cancels 1Claude Code: deny
  • batch_controlPause future dispatch, resume, or cancel remaining steps on explicit user request.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Pause future dispatch, resume, or cancel remaining steps on explicit user request. Already submitted work finishes safely and remains visible.

    Annotations the server declares

    • title: Pause, resume or cancel plan
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Changes things 17Claude Code: ask
  • asset_uploadUpload 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.No findings

    Why it is in this group

    • The name "asset_upload" says "upload": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Upload file to private library
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • batch_repairOn user request, replace arguments of a definitively rejected failed step that has no accepted request ID.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Repair failed plan step
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • batch_submitSave the entire plan once and immediately hand the returned dashboard URL to the user.No findings

    Why it is in this group

    • The name "batch_submit" says "submit": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Submit production plan
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • edit_createSubmit edit work for the authenticated account.No findings

    Why it is in this group

    • The name "edit_create" says "edit": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Edit image
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • image_createSubmit image work for the authenticated account.No findings

    Why it is in this group

    • The name "image_create" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create image
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • media_createSubmit media work for the authenticated account.Reads text others write2 findings

    Why it is in this group

    • The name "media_create" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The input schema at properties.source_url.description mentions "credentials".

      Matched text

      inputSchema.properties.source_url.description: "...S URL,10–2048 characters. No playlists, credentials or non-443 ports. The backend validates..."

      What this check looks for
    • Info

      The input schema at description mentions "credentials".

      Matched text

      inputSchema.description: "...horts/Live/TikTok video URL. Playlists, credentials, IP hosts, custom ports and other websi..."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Analyze public video
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • media_library_clipCut 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Cut clip from library item
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • movie_asset_timing_setSave verified source timestamps for owned audio.No findings

    Why it is in this group

    • The name "movie_asset_timing_set" says "set": a word for a change.
    Description, as the server wrote it
    Save verified source timestamps for owned audio. Times are original-file seconds, not movie offsets. Never invent alignment from transcript length.

    Annotations the server declares

    • title: Save audio timing
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • movie_createSubmit movie work for the authenticated account.1 finding

    Why it is in this group

    • The name "movie_create" says "create": a word for a change.

    Findings

    • Info

      The input schema at $defs.BlenderProgram.properties.python.description mentions "credentials".

      Matched text

      inputSchema.$defs.BlenderProgram.properties.python.description: "...sets and output dimensions. No network, credentials, external packages or GPU."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Compose movie
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • music_createSubmit music work for the authenticated account.No findings

    Why it is in this group

    • The name "music_create" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create music
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • request_getRead request status, progress, results and analysis text.1 finding

    Why it is in this group

    • The name "request_get" says "request": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "request_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "request_get" says "request": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Read request status, progress, results and analysis text.

    Annotations the server declares

    • title: Get request status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • requests_listList work history for one studio.1 finding

    Why it is in this group

    • The name "requests_list" says "request": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "requests_list" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "requests_list" says "request": a word for a change.

      What this check looks for
    Description, as the server wrote it
    List work history for one studio.

    Annotations the server declares

    • title: List studio requests
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sfx_createSubmit sfx work for the authenticated account.No findings

    Why it is in this group

    • The name "sfx_create" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Generate sound effects
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • upscale_createSubmit upscale work for the authenticated account.1 finding

    Why it is in this group

    • The name "upscale_create" says "create": a word for a change.

    Findings

    • Info

      The input schema at properties.source_url.description mentions "credentials".

      Matched text

      inputSchema.properties.source_url.description: "...TTPS image URL, max 2048 characters; no credentials, IP literals, non-443 ports or private..."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Upscale image
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • video_createSubmit video work for the authenticated account.No findings

    Why it is in this group

    • The name "video_create" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create video clip
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • voice_createSubmit voice work for the authenticated account.No findings

    Why it is in this group

    • The name "voice_create" says "create": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create voice
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • workflow_getStart here: read the HiruAI workflow without installing skills.1 finding

    Why it is in this group

    • The name "workflow_get" says "get": a word for reading.
    • The description's first verb is "start": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "workflow_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "workflow_get" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Read workflow and recipes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 16Show 16 read-only tools
  • assets_listList your reusable image, video, voice, music and sound effect assets.No findings

    Why it is in this group

    • The name "assets_list" says "list": a word for reading.
    Description, as the server wrote it
    List your reusable image, video, voice, music and sound effect assets.

    Annotations the server declares

    • title: List my assets
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • batch_getRead one plan, steps and results when requested.No findings

    Why it is in this group

    • The name "batch_get" says "get": a word for reading.
    Description, as the server wrote it
    Read one plan, steps and results when requested. Prefer handing off its URL after submission.

    Annotations the server declares

    • title: Get production plan
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • batch_validateValidate a dependency-ordered plan without starting jobs or consuming studio quota.No findings

    Why it is in this group

    • The name "batch_validate" says "validate": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Validate production plan
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • batches_listList plans owned by this account when the user asks; do not use a polling loop.No findings

    Why it is in this group

    • The name "batches_list" says "list": a word for reading.
    Description, as the server wrote it
    List plans owned by this account when the user asks; do not use a polling loop.

    Annotations the server declares

    • title: List production plans
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • blender_program_validateValidate a Blender bpy Python program, output contract and CPU limits without execution or GPU jobs.1 finding

    Why it is in this group

    • The name "blender_program_validate" says "validate": a word for reading.

    Findings

    • Info

      The input schema at $defs.BlenderProgram.properties.python.description mentions "credentials".

      Matched text

      inputSchema.$defs.BlenderProgram.properties.python.description: "...sets and output dimensions. No network, credentials, external packages or GPU."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Validate Blender program
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • capabilities_getRead live studio input schemas, supported outputs and planning rules before making a plan.No findings

    Why it is in this group

    • The name "capabilities_get" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Read capabilities
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • dopamine_hooks_getRead the creative baseline catalog: everyday situations in which people feel reward and anticipation (dopamine hooks), each with visual, audio and situation cues and guardrails, pl…No findings

    Why it is in this group

    • The name "dopamine_hooks_get" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Read dopamine hooks
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • image_models_getRead the same image-model catalog as image.hiruai.com: current execution availability, traits, dated Arena evidence, model-specific consent and ChatGPT/Claude native-image alternat…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "image_models_get" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "chat": it reads messages.
    • untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Compare image models
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • media_library_getRead one library item's AI-ready manifest (schema hiruai.media-library.v1): provenance and reuse guidance, renditions, catalog (summary, chapters, reusable_segments, voice_referenc…No findings

    Why it is in this group

    • The name "media_library_get" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get media library item
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • media_library_listList the account's media library (own recordings and referenced YouTube/TikTok/Instagram Reels/web videos) with status, tags, summary and reuse_policy.Reads text others writeNo findings

    Why it is in this group

    • The name "media_library_list" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "web": it reads web pages, which anyone can write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List media library
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • movie_asset_metadataInspect actual audio duration, bounded waveform and imported subtitle cues without generation or GPU jobs.No findings

    Why it is in this group

    • The description's first verb is "inspect": a word for reading.
    Description, as the server wrote it
    Inspect actual audio duration, bounded waveform and imported subtitle cues without generation or GPU jobs.

    Annotations the server declares

    • title: Inspect audio asset
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • movie_plan_validateValidate an edit against owned real source durations, mapped narration cues and layer limits.1 finding

    Why it is in this group

    • The name "movie_plan_validate" says "validate": a word for reading.

    Findings

    • Info

      The input schema at $defs.BlenderProgram.properties.python.description mentions "credentials".

      Matched text

      inputSchema.$defs.BlenderProgram.properties.python.description: "...sets and output dimensions. No network, credentials, external packages or GPU."

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Validate movie edit
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • movie_script_analyzeGet stable sentence IDs from the exact planned Voice text BEFORE generation.No findings

    Why it is in this group

    • The name "movie_script_analyze" says "analyze": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Analyze narration script
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • result_readRead a completed output in base64 chunks (up to 1 MiB).No findings

    Why it is in this group

    • The name "result_read" says "read": a word for reading.
    Description, as the server wrote it
    Read a completed output in base64 chunks (up to 1 MiB). Follow next_offset until null. Binary files remain private.

    Annotations the server declares

    • title: Read result file
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • video_reference_capabilitiesRead the deployed Video reference paths and GPU validation status.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read the deployed Video reference paths and GPU validation status. Distinguishes endpoint keyframes from full-video depth/canny/pose IC-LoRA. No generation.

    Annotations the server declares

    • title: Read video reference support
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:20 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
18
Protocol version
2025-11-25
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.hiruai.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.hiruai.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 18 tools that change things (1 destructive, 17 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.hiruai.com/mcp: tools/list returned 34 tools to an anonymous client, including batch_control (destructive), image_create (write), edit_create (write), upscale_create (write), voice_create (write) and 13 more

    What this check looks for

Posture changes

  1. Nov 21, 2026
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 18
    • Protocol version: none to 2025-11-25
    • WWW-Authenticate on 401: yes to not observed
    • resource_metadata in WWW-Authenticate: https://mcp.hiruai.com/.well-known/oauth-protected-resource to none
    • RFC 9728 protected resource metadata: https://mcp.hiruai.com/.well-known/oauth-protected-resource to https://mcp.hiruai.com/.well-known/oauth-protected-resource/mcp

Findings

Matches of fixed checks, with the text they matched.

3 warn6 info
  • The server marks "requests_list" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "requests_list" says "request": a word for a change.

    What this check looks for
  • The server marks "request_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "request_get" says "request": a word for a change.

    What this check looks for
  • The server marks "workflow_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "workflow_get" says "get": a word for reading.

    What this check looks for
  • The input schema at properties.source_url.description mentions "credentials".

    Matched text

    inputSchema.properties.source_url.description: "...TTPS image URL, max 2048 characters; no credentials, IP literals, non-443 ports or private..."

    What this check looks for
  • The input schema at $defs.BlenderProgram.properties.python.description mentions "credentials".

    Matched text

    inputSchema.$defs.BlenderProgram.properties.python.description: "...sets and output dimensions. No network, credentials, external packages or GPU."

    What this check looks for
  • The input schema at properties.source_url.description mentions "credentials".

    Matched text

    inputSchema.properties.source_url.description: "...S URL,10–2048 characters. No playlists, credentials or non-443 ports. The backend validates..."

    What this check looks for
Show 3 more findings
  • The input schema at description mentions "credentials".

    Matched text

    inputSchema.description: "...horts/Live/TikTok video URL. Playlists, credentials, IP hosts, custom ports and other websi..."

    What this check looks for
  • The input schema at $defs.BlenderProgram.properties.python.description mentions "credentials".

    Matched text

    inputSchema.$defs.BlenderProgram.properties.python.description: "...sets and output dimensions. No network, credentials, external packages or GPU."

    What this check looks for
  • The input schema at $defs.BlenderProgram.properties.python.description mentions "credentials".

    Matched text

    inputSchema.$defs.BlenderProgram.properties.python.description: "...sets and output dimensions. No network, credentials, external packages or GPU."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 401 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 18 (and 4 more).View diff
    • HTTP status of an anonymous initialize: 401 to 200
    • tools/list served without credentials: no to yes
    • Tools that change things, listed without credentials: 0 to 18
    • Protocol version: none to 2025-11-25
    • WWW-Authenticate on 401: yes to not observed
    • resource_metadata in WWW-Authenticate: https://mcp.hiruai.com/.well-known/oauth-protected-resource to none
    • RFC 9728 protected resource metadata: https://mcp.hiruai.com/.well-known/oauth-protected-resource to https://mcp.hiruai.com/.well-known/oauth-protected-resource/mcp

Install

Pinned to version 1.3.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http creative-cloud https://mcp.hiruai.com/mcp
claude mcp add --transport http creative-cloud https://mcp.hiruai.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__creative-cloud__image_models_get",
      "mcp__creative-cloud__assets_list",
      "mcp__creative-cloud__result_read",
      "mcp__creative-cloud__blender_program_validate",
      "mcp__creative-cloud__movie_script_analyze",
      "mcp__creative-cloud__movie_asset_metadata",
      "mcp__creative-cloud__movie_plan_validate",
      "mcp__creative-cloud__capabilities_get",
      "mcp__creative-cloud__batch_validate",
      "mcp__creative-cloud__batches_list",
      "mcp__creative-cloud__batch_get",
      "mcp__creative-cloud__media_library_list",
      "mcp__creative-cloud__media_library_search",
      "mcp__creative-cloud__media_library_get",
      "mcp__creative-cloud__dopamine_hooks_get",
      "mcp__creative-cloud__video_reference_capabilities"
    ],
    "ask": [
      "mcp__creative-cloud__image_create",
      "mcp__creative-cloud__edit_create",
      "mcp__creative-cloud__upscale_create",
      "mcp__creative-cloud__voice_create",
      "mcp__creative-cloud__music_create",
      "mcp__creative-cloud__sfx_create",
      "mcp__creative-cloud__video_create",
      "mcp__creative-cloud__movie_create",
      "mcp__creative-cloud__media_create",
      "mcp__creative-cloud__asset_upload",
      "mcp__creative-cloud__requests_list",
      "mcp__creative-cloud__request_get",
      "mcp__creative-cloud__movie_asset_timing_set",
      "mcp__creative-cloud__workflow_get",
      "mcp__creative-cloud__batch_submit",
      "mcp__creative-cloud__batch_repair",
      "mcp__creative-cloud__media_library_clip"
    ],
    "deny": [
      "mcp__creative-cloud__batch_control"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as creative-cloud. Review it before you use it.

Capability tags behind 3 rules
  • mcp__creative-cloud__media_create untrusted-input
  • mcp__creative-cloud__image_models_get private-data, untrusted-input
  • mcp__creative-cloud__media_library_list untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.hiruai/creative-cloud/verify?hash=d10640628a5a953966381d422ba4281ea565421364c502a32b024f886a6a69ee" | jq -e '.changed == false'

Pinned hash d10640628a5a, from Nov 20, 2026, 04:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.hiruai/creative-cloud/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.hiruai/creative-cloud
[![Anlyon Radar](https://radar.anlyon.com/badge/com.hiruai/creative-cloud.svg)](https://radar.anlyon.com/servers/com.hiruai/creative-cloud)

Source: MCP Registry. Synced Nov 20, 2026, 05:17 UTC.

HiruAI Creative Cloud MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the HiruAI Creative Cloud MCP server safe?

No scan can promise that. What its definitions show: 34 tools, 18 of which can change, send or delete something, and 9 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the HiruAI Creative Cloud MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: batch_control.

Can the HiruAI Creative Cloud MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the HiruAI Creative Cloud MCP server have?

34 tools: 1 destructive, 17 write, 16 read. batch_control, image_create, edit_create, upscale_create, voice_create, music_create, sfx_create, video_create and 26 more.

Does the HiruAI Creative Cloud MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the HiruAI Creative Cloud MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the HiruAI Creative Cloud MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.