Brainiall Image

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Background removal, upscaling, face restore, document OCR, table extraction, visual understanding.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Brainiall Image": {
      "url": "https://api.brainiall.com/mcp/image/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (10)

• remove_background read-only

  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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• upscale_image read-only

  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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• restore_face read-only

  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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• check_image_service read-only

  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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• document_extract read-only

  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).

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• document_query read-only

  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).

  Parameters:

  • image (required) — string — Base64-encoded PNG/JPEG of the document page
  • question (required) — string — The natural-language question about the document

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• document_tables read-only

  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.

  Parameters:

  • image (required) — string — Base64-encoded PNG/JPEG of the document page

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• document_to_markdown read-only

  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.

  Parameters:

  • pdf (required) — string — Base64-encoded PDF document
  • page_range — Page range like '1,2,5-10' or null for all pages

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• run_skillsets read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• understand_content read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.