com.brainiall/image

Est-ce que com.brainiall/image est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.brainiall/image » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 10 outils

• check_image_service≈ 130 tokens

  Check health status of Image API services and loaded models. Returns: dict with keys: - status (str): 'healthy' or error state - models (dict): Loaded model status per capability - version (str): API version

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "check_image_service", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• document_extract≈ 237 tokens

  Turn a document image into structured fields. doc_type picks the schema (receipt/invoice/id/contract/form/generic). A page with no readable text returns an error rather than a guess. Returns: dict with keys: doc_type (str), fields (dict — null for any value not present), text (str — the recognised plain text).

  Paramètres, retour & exemple (2)

  Paramètres

  • image · string · requis
    Base64-encoded PNG/JPEG of a single document page
  • doc_type · string · optionnel
    The document kind — picks the field schema: receipt | invoice | id | contract | form | generic | business_card | w2 | health_card | mortgage | pay_stub

  Exemple d'appel

  {"name": "document_extract", "arguments": {"image": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• document_query≈ 209 tokens

  Ask a natural-language question about a document image; returns a grounded answer plus the supporting line. Returns found:false rather than guessing when the document doesn't contain the answer. Returns: dict with keys: answer (str|null), found (bool), supporting_text (str|null), text (str).

  Paramètres, retour & exemple (2)

  Paramètres

  • image · string · requis
    Base64-encoded PNG/JPEG of the document page
  • question · string · requis
    The natural-language question about the document

  Exemple d'appel

  {"name": "document_query", "arguments": {"image": "texte", "question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• document_tables≈ 154 tokens

  Reconstruct every table in a document image into headers and rows. Returns: dict with keys: table_count (int), tables (list of {title, headers, rows, row_count, column_count}); [] if there are no tables.

  Paramètres, retour & exemple (1)

  Paramètres

  • image · string · requis
    Base64-encoded PNG/JPEG of the document page

  Exemple d'appel

  {"name": "document_tables", "arguments": {"image": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• document_to_markdown≈ 181 tokens

  Return the document as structured Markdown (headings, tables, lists, code blocks, math). Brainiall Doc Layout engine. The single API for converting documents to LLM-friendly format.

  Paramètres, retour & exemple (2)

  Paramètres

  • pdf · string · requis
    Base64-encoded PDF document
  • page_range · ? · optionnel
    Page range like '1,2,5-10' or null for all pages

  Exemple d'appel

  {"name": "document_to_markdown", "arguments": {"pdf": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• remove_background≈ 311 tokens

  Remove the background from an image. Uses Brainiall Cutout engine segmentation to precisely separate foreground from background. Returns a base64-encoded image with transparent background (PNG) or white background (WebP). Sub-500ms latency on GPU. Args: image_base64: Base64-encoded image data (PNG, JPEG, or WebP). output_format: Output format -- 'png' (with transparency) or 'webp'. Returns: dict with keys: - image_base64 (str): Base64-encoded result image - format (str): Output image format - original_size (dict): Original width and height - processing_ms (int): Processing time in milliseconds

  Paramètres, retour & exemple (2)

  Paramètres

  • image_base64 · string · requis
    Base64-encoded image data. Supports PNG, JPEG, and WebP formats.
  • output_format · string · optionnel
    Output image format: 'png' (default, with transparency) or 'webp'

  Exemple d'appel

  {"name": "remove_background", "arguments": {"image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• restore_face≈ 396 tokens

  Restore and enhance faces in an image with the Brainiall face-restoration engine. Detects all faces via RetinaFace, restores quality (fixes blur, noise, compression artifacts), and pastes them back. Optionally enhances the background with the Brainiall image-upscaling engine. GPU-accelerated, sub-3s latency. Args: image_base64: Base64-encoded image data containing faces (PNG, JPEG, WebP). upscale: Output upscale factor -- 1 to 4 (default: 2). enhance_background: Whether to enhance background with the Brainiall image-upscaling engine (default: true). Returns: dict with keys: - image (str): Base64-encoded restored image - format (str): Output image format - width (int): Output width - height (int): Output height - upscale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds

  Paramètres, retour & exemple (3)

  Paramètres

  • upscale · integer · optionnel
    Output upscale factor: 1-4 (default: 2)
  • image_base64 · string · requis
    Base64-encoded image data containing one or more faces.
  • enhance_background · boolean · optionnel
    Enhance background with the Brainiall image-upscaling engine (default: true)

  Exemple d'appel

  {"name": "restore_face", "arguments": {"image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• run_skillsets≈ 224 tokens

  Run a multi-skill enrichment pipeline over a document image or text in one call. Brainiall Skillsets engine. Returns per-skill outputs ready for indexing or RAG.

  Paramètres, retour & exemple (3)

  Paramètres

  • text · ? · optionnel
    Pre-extracted text (skip OCR)
  • image · ? · optionnel
    Base64 image (triggers OCR)
  • skills · ? · optionnel
    Enrichment skills: ocr | entities | language | keyphrases | sentiment

  Exemple d'appel

  {"name": "run_skillsets", "arguments": {"text": "texte", "image": "texte", "skills": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• understand_content≈ 248 tokens

  Multimodal extraction. Send an image, text, or both; define your schema of fields; get structured JSON. Brainiall Content Understanding engine. Unified multimodal field extraction over images and text.

  Paramètres, retour & exemple (3)

  Paramètres

  • text · ? · optionnel
    Optional pre-extracted text
  • image · ? · optionnel
    Optional base64 image (will OCR first)
  • field_schema · ? · optionnel
    Map of field_name -> description, e.g. {"invoice_id":"invoice number","total":"amount due"}

  Exemple d'appel

  {"name": "understand_content", "arguments": {"text": "texte", "image": "texte", "field_schema": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• upscale_image≈ 312 tokens

  Upscale image resolution with the Brainiall image-upscaling engine. Enhances image resolution by 2x or 4x with the GPU-accelerated Brainiall image-upscaling engine super-resolution. Processes in tiles (256x256) to manage VRAM. Maximum output dimension: 8192x8192. Args: image_base64: Base64-encoded image data (PNG, JPEG, or WebP). scale: Upscale factor -- 2 or 4 (default: 4). Returns: dict with keys: - image (str): Base64-encoded upscaled image - format (str): Output image format - width (int): Output width - height (int): Output height - scale (int): Scale factor applied - processing_time_ms (float): Processing time in milliseconds

  Paramètres, retour & exemple (2)

  Paramètres

  • scale · integer · optionnel
    Upscale factor: 2 or 4 (default: 4)
  • image_base64 · string · requis
    Base64-encoded image data. Supports PNG, JPEG, and WebP formats.

  Exemple d'appel

  {"name": "upscale_image", "arguments": {"image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.brainiall.com/mcp/image/mcp