# Arckep MCP server

Source: https://glimind.com/server/mcp-registry%2Fru.arckep%2Fmcp
Registry id: `mcp-registry/ru.arckep/mcp`
Status: live (checked 2026-11-22T15:58:52.948Z)

## Measurements (30 days)

- Uptime: 99.75%
- Checks: 716
- Outages (90 days): 3

## Install

```json
{
  "mcpServers": {
    "arckep-mcp-server": {
      "type": "http",
      "url": "https://arckep.ru/api/v1/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http arckep-mcp-server https://arckep.ru/api/v1/mcp
```

## Tools (98)

- `cancel_chat_batch`: Cancel an in-progress chat batch.
- `cancel_document`: Stop the agent's current turn. The document stays (status awaiting_input), so revise_document can follow.
- `cancel_higgsfield_video`: Cancel a Higgsfield video that is still queued at the provider and refund the charge. Fails once the provider has started the video.
- `cancel_presentation`: Stop the agent's current turn. The presentation stays (status awaiting_input), so revise_presentation can follow.
- `chat_completion`: Run a paid chat completion. Pass model and messages (plus optional free data_guard=true to scrub PII/requisites before sending to the provider and unmask the re
- `check_3d_rig`: Run free (0 RUB) Tripo v3 pre-rigging check on an owned completed 3D job (source_job_id) or public HTTPS 3D model_url.
- `complete_book_upload`: Complete a direct multipart S3 upload for a book scan and verify its real byte size in S3.
- `create_3d`: Start a paid 3D job. Request follows POST /api/v1/models3d/generations (for model='idol', pass 1 image_url; for model='idol-max', pass 1 image_url with idol_var
- `create_3d_process`: Start a paid Direct Tripo v3 or Meshy Retexture post-processing job (rig, retarget, rig_and_retarget, texture with texture_model='tripo' | 'meshy-n1-retexture' 
- `create_book`: Create a book or document digitization order from a public HTTPS file_url (up to 100 MiB) or a completed multipart upload key (up to 500 MiB). Accepts PDF, DjVu
- `create_book_ticket`: Submit a manual correction note (kind='correction') or quality/refund review request (kind='defect') to the studio team.
- `create_book_upload`: Initialize a direct multipart S3 upload for a book scan up to 500 MiB (PDF, DjVu, ZIP/CBZ archive, image, or Office document). Returns key, upload_id, part_size
- `create_chat_batch`: Create a paid text-only OpenAI, Anthropic or Gemini chat batch with a caller-supplied idempotency key. Use a model advertising batch capability; up to 50,000 it
- `create_document`: Start a Word, Excel or PDF document built by Claude (POST /api/v1/documents). Paid by actual usage. The balance is charged when the agent finishes each turn; a 
- `create_higgsfield_cinema`: Start a paid Higgsfield Cinema Studio 4.0 video (POST /api/v1/higgsfield/cinema/generate). Needs prompt. duration is 4-30 seconds; resolution 480p or 720p. Refe
- `create_higgsfield_genjutsu`: Start a paid Higgsfield Genjutsu video (POST /api/v1/higgsfield/genjutsu/{kind}/generate). kind motion/swap selects Genjutsu: source 4-30 s (swap: at least 4096
- `create_higgsfield_restyle`: Start a paid Higgsfield Genjutsu Restyle video (POST /api/v1/higgsfield/genjutsu/restyle/generate). Redraws the whole source video in one chosen style; motion, 
- `create_higgsfield_wan_prime`: Start a paid Wan 3.0 Prime video (POST /api/v1/higgsfield/wan-prime/generate). Needs prompt. duration is 2-30 seconds; resolution 480p, 720p (default) or 1080p;
- `create_image`: Start a paid image job. Request needs model and prompt; max_cost_rub is optional. For topaz-image-upscale, crystal-upscale or runway-image-upscale use create_im
- `create_image_upscale`: Start an async image upscale job (202 Accepted). Poll GET /api/v1/images/generations/{id} for the result.
- `create_lightx_recamera`: Start paid LightX recamera on an owned source video. First call estimate_lightx_recamera with the same source video and camera settings. max_cost_rub is require
- `create_lightx_relight`: Start paid LightX relight on an owned source video. First call estimate_lightx_relight with the same source video and lighting settings. max_cost_rub is require
- `create_marketplace_cards`: Start a pack of product cards for Wildberries or Ozon (POST /api/v1/marketplace-cards/generations). Paid. From 1-8 photos of one product and its description the
- `create_presentation`: Start a PowerPoint presentation built by Claude (POST /api/v1/presentations). Paid by actual usage. The balance is charged when the agent finishes each turn; a 
- `create_speech`: Generate Gemini speech synchronously, returning a completed result with a WAV URL. Supports style, two-speaker turns and owned custom voices. Reuse idempotency_
- `create_transcription`: Transcribe base64 audio, up to 10 MiB. Larger files use the HTTP multipart API. Completes synchronously. Keep the same idempotency_key on retries after a timeou
- `create_video`: Start a paid video job. Request follows POST /api/v1/videos/generations (supports mode="t2v", "i2v", "r2v", "edit", "extend", and "a2v" with audio_url + optiona
- `create_video_alpha_gen`: Start paid LTX 2.5 Alpha-Gen video background removal without green screen. Produces a primary MP4 with source audio (`background_mode` = `checkerboard`, `solid
- `create_video_camera`: Start paid MiniMax camera-controls on an owned starting image. First call estimate_video_camera with the same image and camera settings. max_cost_rub is require
- `create_video_relight`: Start paid MiniMax relight using an owned video and an owned lighting-sphere reference image. First call estimate_video_relight with the same media and settings
- `create_video_upscale`: Launch an async video upscale job (202 Accepted). Poll GET /api/v1/videos/upscale/generations/{id}.
- `decide`: Ask a typed decision: Jev (typesafe/jev-1.13: text state + questions object), GPT-6 Luna Decisions (openai/gpt-6-luna-decisions: input text or user messages wit
- `delete_speech_voice`: Delete one of your own custom voices (id from list_my_speech_voices). A stored voice is also removed at Google.
- `design_speech_voice`: Create a custom voice from a text description. Free; the voice lives 365 days. request: display_name, prompt (10-1000 characters: age, timbre, pace, manner, acc
- `download_3d_stl`: Download a completed 3D job as base64 binary STL or 3MF, without new provider billing.
- `estimate_3d`: Quote a 3D job. Pass the API model, prompt or image_url(s) and quality settings (rodin-v2.5: variant, high_pack, tpose; idol: image_url, image_type, num_gaussia
- `estimate_3d_process`: Quote exact RUB price for Direct Tripo v3 or Meshy Retexture (texture_model='tripo' | 'meshy-n1-retexture' | 'meshy-v7-retexture') rigging, animation retargetin
- `estimate_book`: Quote the current per-page rate and full book price in RUB, with account discount, without charging. Pass book_id once get_book reaches status ready/sampled to 
- `estimate_chat_document`: Quote document pages locally without provider fees. MCP uploads up to 10 MiB; HTTP up to 32 MiB.
- `estimate_document`: Typical cost of a Word, Excel or PDF document in RUB; nothing is charged and nothing is started. Documents are priced by actual usage (the real Claude session c
- `estimate_higgsfield_cinema`: Quote a Higgsfield Cinema Studio 4.0 video (higgsfield-cinema-4) in RUB; nothing is charged. Same request as create_higgsfield_cinema (webhook_url is accepted a
- `estimate_higgsfield_genjutsu`: Quote a Higgsfield Genjutsu video in RUB; nothing is charged. kind motion/swap selects Genjutsu; light-motion/light-swap selects Genjutsu Light. Light uses the 
- `estimate_higgsfield_restyle`: Quote a Higgsfield Genjutsu Restyle video in RUB; nothing is charged. Same request as create_higgsfield_restyle. The price depends on the source video length an
- `estimate_higgsfield_wan_prime`: Quote a Wan 3.0 Prime video (higgsfield-wan-3-prime) in RUB; nothing is charged. Same request as create_higgsfield_wan_prime (webhook_url is accepted and ignore
- `estimate_image`: Quote an image job. Pass API fields such as model, num_images, quality and resolution. For topaz-image-upscale, crystal-upscale or runway-image-upscale use esti
- `estimate_image_upscale`: Estimate exact cost and output dimensions for Topaz, Crystal, or Runway Magnific image upscale.
- `estimate_lightx_recamera`: Quote the maximum hold for LightX recamera; nothing is charged. Required video_url is an owned source video (at least 49/24 seconds and at most 15 seconds, up t
- `estimate_lightx_relight`: Quote the maximum hold for LightX relight; nothing is charged. Required video_url is an owned source video (at least 49/24 seconds and at most 15 seconds, up to
- `estimate_marketplace_cards`: Price range of a Wildberries / Ozon card pack in RUB; nothing is charged and nothing is started. The planner chooses the slide count (3-12 here, 4 by default), 
- `estimate_ocr_document`: Quote standalone OCR pages locally without provider fees. MCP uploads up to 10 MiB; HTTP up to 32 MiB.
- `estimate_presentation`: Typical cost of a presentation in RUB; nothing is charged and no deck is started. Presentations are priced by actual usage (the real Claude session cost times r
- `estimate_speech`: Estimate Gemini speech cost. Approximate: actual text and audio tokens determine the charge.
- `estimate_transcription`: Estimate speech-to-text cost for a model and duration in seconds.
- `estimate_video`: Quote a video job. Pass API fields such as model, mode, duration_seconds, resolution, fps, camera_motion, auto_duration (LTX-2.5), smart_duration (or duration_s
- `estimate_video_alpha_gen`: Quote LTX 2.5 Alpha-Gen background removal for an owned source video without charging. Measures source duration and dimensions (`<=200 MiB`, `2..3072` frames, `
- `estimate_video_camera`: Quote the maximum hold for MiniMax camera-controls; nothing is charged. Required image_url is an owned starting image; pass prompt plus one camera control (free
- `estimate_video_relight`: Quote the maximum hold for MiniMax relight; nothing is charged. Required video_url and reference_image_url are owned uploaded media; the image is a lighting sph
- `estimate_video_upscale`: Estimate cost for Topaz, FLUX, Runway Magnific, or LTX 2.5 video upscaling.
- `get_3d`: Get the status, cost and output of one 3D job.
- `get_balance`: Get the effective personal or corporate balance in RUB.
- `get_book`: Get the status, page progress, sample verdict, RUB billing, QC summary and signed download URLs of one book. status lifecycle: splitting -> ready -> (optional s
- `get_book_report`: Get the structured quality report of a finished book (summary counts, detected chapters, printed TOC diff, QC checks, per-page agreement).
- `get_chat_batch`: Get one chat batch and its provider status.
- `get_chat_batch_results`: Get completed batch items and their final charges. Paginated: limit 1-1000 (default 1000), offset >= 0. Follow next_offset while has_more is true; total is the 
- `get_document`: Get the status, cost and files of one document. status: pending/running (the agent is working: ask again in a minute or two), awaiting_input (a turn is done: re
- `get_image`: Get the status, cost and output of one image job. Defaults to the format requested at creation. b64_json adds original file bytes to output.images (up to 16 MiB
- `get_marketplace_cards`: Get the status, cost and pictures of one card pack. status: queued/processing (the pack is being built: progress_pct says how far, ask again in a minute or two)
- `get_presentation`: Get the status, cost and files of one presentation. status: pending/running (the agent is working: ask again in a minute or two), awaiting_input (a turn is done
- `get_speech`: Get owned completed Gemini speech with a fresh WAV download URL.
- `get_usage`: Get RUB spend of the caller's API keys: today, last 7 days, the last `days` (1-90), per day and per model, plus the balance and an estimate of the days it lasts
- `get_video`: Get the status, cost and output of one video job, including Higgsfield, camera, relight and ltx-2.5-alpha-gen jobs.
- `get_video_upscale`: Get status, reconciled billing fields, and signed output URLs for a video upscale job.
- `list_3d`: List the caller's 3D jobs, newest first.
- `list_book_pages`: List verified page texts and multi-engine agreement scores of a book (pass sample_only=true after a free sample probe).
- `list_books`: List the caller's book digitization orders, newest first (id, title, status, page_count, pages_done, billing).
- `list_chat_batches`: List recent public chat batches.
- `list_documents`: List the caller's documents (id, format, title, status, version, cost), newest first. Files are in get_document.
- `list_higgsfield_restyle_styles`: List the visual styles Higgsfield Genjutsu Restyle can apply (nothing is charged). Each item has id, name (English), name_ru and preview_url. Pass the chosen id
- `list_images`: List the caller's image jobs, newest first.
- `list_marketplace_cards`: List the caller's finished card packs, newest first (id, marketplace, title, cost, pictures). before_id is the id of the last pack already seen. A pack that is 
- `list_models`: List image, video, 3D, chat, decision, STT and TTS models exposed by the public API. Each model includes a human-readable description and capability tags. Use m
- `list_my_speech_voices`: List the caller's unexpired custom Google voices, created in the studio or with this API. Use a voice's id as custom_voice_id in create_speech. saved_limit is h
- `list_presentations`: List the caller's presentations (id, title, status, version, cost), newest first. Files are in get_presentation.
- `list_speech`: List the caller's completed Gemini speech (studio and API), newest first.
- `list_speech_voices`: List Google's prebuilt voices without generating audio.
- `list_video_upscales`: List video upscale jobs for the API key owner (newest first).
- `list_videos`: List the caller's video jobs, newest first.
- `ocr_document`: Run standalone DeepSeek OCR on a PDF, Office document, or image and return page-by-page text. MCP uploads up to 10 MiB; use HTTP for files up to 32 MiB. Support
- `parse_chat_document`: Parse a document once for DeepSeek Flash; retain the returned id and reuse it in document_ids. Requires an 8 to 128 character idempotency_key; reuse it after a 
- `replicate_speech_voice`: Clone a voice from a recording. Free. Only for a voice whose owner has agreed to be cloned. source_audio_base64: the voice sample. consent_audio_base64: the sam
- `revise_document`: Send the agent a message about a document (POST /api/v1/documents/{id}/messages). Paid by actual usage. request.text is a change request ("add a section on risk
- `revise_presentation`: Send the agent a message about a presentation (POST /api/v1/presentations/{id}/messages). Paid by actual usage. request.text is a change request ("shorten slide
- `scrub_data`: Scrub personal data, company names, requisites, secrets, optional commercial terms, custom_terms ([УСЛОВИЕ_N]), named custom_labels ({'ПРОЕКТ': ['Арктика-2']} -
- `start_book`: Start either a one-time free quality probe (mode='sample', up to 10 evenly spaced pages) or paid full digitization (mode='full'). mode='sample' requires status 
- `unmask_data`: Restore original names and requisites from placeholders like [ЛИЦО_1] in the right Russian grammatical case using data_guard_token from scrub_data or chat_compl
- `upload_media`: Upload an image, video (mp4/webm), audio (mp3/wav/m4a/aac), 3D mesh (glb, gltf, fbx, obj, stl), or a document for a presentation or document job, up to 10 MiB, 
- `web_fetch`: Read one web page (http/https url) and return its text as Markdown. Charges a flat RUB price per page that is read; a page that cannot be read is free.
- `web_search`: Search the web: ranked results with title, url, snippet and a longer summary. Pass need_content=true for the page text. Charges a flat RUB price per request tha

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
