com.mart402/vision

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

Calibrated vision for AI agents: meal nutrition, personal color, styling reports. x402, no API key.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "vision": {
      "url": "https://mart402.com/mcp/vision",
      "transport": "streamable-http"
    }
  }
}

Measured tools (9)

• get_catalog read-only

  Mart402 product catalog: all products, prices, payment config, error codes, rate limits. Free.

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

• get_receipt read-only

  Re-fetch a previously paid result for free by receipt id (every paid response carries receipt_id).

  Parameters:

  • receipt_id (required) — string — receipt_id from a paid response (rcpt_...)

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

• get_sample read-only

  Free recorded sample response for a paid product (from real production runs, marked sample:true) - see the exact response shape before paying anything. Available: document-pipeline, enrich, extract, jp-bonus-net, jp-business-days, jp-company, jp-consumption-tax, jp-crypto-tax, jp-dependent-threshold, jp-mortgage, jp-overtime-wage, jp-payroll-net, jp-payroll-suite, jp-payslip-audit, jp-retirement-tax, jp-social-insurance, meal-vision, ocr, parse, pdf-info, pdf-merge, pdf-pages, portrait-analysis, report-pack, structured, style-profile, style-report, verify.

  Parameters:

  • product (required) — string — One of: document-pipeline, enrich, extract, jp-bonus-net, jp-business-days, jp-company, jp-consumption-tax, jp-crypto-tax, jp-dependent-threshold, jp-mortgage, jp-overtime-wage, jp-payroll-net, jp-payroll-suite, jp-payslip-audit, jp-retirement-tax, jp-social-insurance, meal-vision, ocr, parse, pdf-info, pdf-merge, pdf-pages, portrait-analysis, report-pack, structured, style-profile, style-report, verify. Product id (see the enum)

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

• portrait_precheck read-only

  FREE analyzability check before paying for portrait_analysis: is a face detectable, is the photo quality good enough (clipping/color cast)? Deterministic, no LLM. 10/hour/IP.

  Parameters:

  • image_url — string — Absolute http(s) URL of the image (JPEG/PNG/WebP)
  • image_base64 — string — Base64-encoded image bytes (alternative to image_url)

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

• meal_vision

  Analyze a meal photo to itemized nutrition JSON: dishes, portions, kcal, macros with per-item confidence, reference-object scale calibration, scene-complexity detection, a disclosed calibrated kcal range, PFC balance ratios and alcohol-aware 4/4/9 cross-checks. Calibrated on 30 weighed meals (range contained truth in 26/30). Every call is a 3-run consensus with disclosed spread + item agreement. $0.05/image.

  Parameters:

  • hints — string — cuisine/context hint, e.g. 'Japanese teishoku, small diet portions' - measurably improves accuracy on regional home-style meals
  • image_url — string — Absolute http(s) URL of the image (JPEG/PNG/WebP)
  • pack_code — string — retry credit issued after an unbilled failed call (replaces payment)
  • x_payment — string — Optional: base64 X-PAYMENT header value (x402 exact scheme, USDC on Base mainnet). Omit it to receive the payment requirements (accepts[] + docs) for this call without being charged.
  • image_base64 — string — Base64-encoded image bytes (alternative to image_url)

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

• style_profile

  Integrated styling verdict: seasonal color (measured colorimetry consensus) + face-impression zone (published geometry rules) + body frame + integration rules (palette subset, taste, silhouette, modifiers). 1-3 face photos, optional full-body + questionnaire. Flat $0.05/call. Choose this when you want the integrated styling analysis as JSON to use or render yourself; it is the same analysis that style_report turns into a PDF. For color only use portrait_analysis.

  Parameters:

  • style — string — One of: feminine, masculine, neutral. Styling context: feminine, masculine or neutral
  • images — array — Up to 3 objects {image_url | image_base64}
  • image_url — string — Absolute http(s) URL of the image (JPEG/PNG/WebP)
  • x_payment — string — Optional: base64 X-PAYMENT header value (x402 exact scheme, USDC on Base mainnet). Omit it to receive the payment requirements (accepts[] + docs) for this call without being charged.
  • image_base64 — string — Base64-encoded image bytes (alternative to image_url)
  • questionnaire — object — Optional frame questionnaire answers (see /catalog input spec)
  • body_image_url — string — Optional full-body photo URL for frame estimation
  • body_image_base64 — string — See the product's input spec in /catalog

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

• style_report

  Client-ready deliverable: the style-profile analysis rendered as a finished PDF report in English or Japanese (palette with color names, style-aware outfit formulas, virtual draping boards with disclosed candidate conflicts, honest confidence) returned as report_pdf_base64 + full profile JSON. For agents serving human end-clients. Flat $2.99/call, or $1.99/unit with a prepaid report_pack credit (pass pack_code). Choose this when the result goes to a HUMAN end-client as a finished document; if you will present the result yourself, style_profile returns the same analysis as JSON for less.

  Parameters:

  • name — string — client name printed on the report (same field as REST; client_name is accepted as an alias)
  • style — string — One of: feminine, masculine, neutral. Styling context: feminine, masculine or neutral
  • images — array — 1-3 face photos
  • language — string — report language
  • image_url — string — Absolute http(s) URL of the image (JPEG/PNG/WebP)
  • pack_code — string — prepaid credit from report_pack (replaces payment)
  • x_payment — string — Optional: base64 X-PAYMENT header value (x402 exact scheme, USDC on Base mainnet). Omit it to receive the payment requirements (accepts[] + docs) for this call without being charged.
  • image_base64 — string — Base64-encoded image bytes (alternative to image_url)
  • questionnaire — object — optional answers (see /catalog style-report input)
  • body_image_url — string — optional full-body photo URL (body-shape layer)
  • body_image_base64 — string — optional full-body photo as base64

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

• report_pack

  Volume pricing for style_report: one $19.90 payment returns 10 single-use credit codes ($1.99/unit vs $2.99 single, en or ja, no expiry). Treat codes like cash. Not an analysis: it buys prepaid style_report credits. Choose this only when you expect to produce several style_report PDFs; pass each code as pack_code to style_report.

  Parameters:

  • x_payment — string — Optional: base64 X-PAYMENT header value (x402 exact scheme, USDC on Base mainnet). Omit it to receive the payment requirements (accepts[] + docs) for this call without being charged.

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

• portrait_analysis

  Personal color analysis from 1-3 portraits: measured pixel colorimetry (CIELAB/ITA) cross-checked against vision-model attributes, cross-photo lighting consistency, then a published deterministic rule table gives the 4-season verdict with palette and style advice. No identification; images not stored. Flat $0.05/call. Choose this when you need only the seasonal color verdict and palette as JSON. For the fuller styling verdict (face impression, body frame, silhouette) use style_profile; for a finished PDF for a human client use style_report.

  Parameters:

  • style — string — One of: feminine, masculine, neutral. Styling context: feminine, masculine or neutral
  • images — array — up to 3 of {image_url|image_base64}; different lighting recommended
  • image_url — string — Absolute http(s) URL of the image (JPEG/PNG/WebP)
  • pack_code — string — retry credit issued after an unbilled failed call (replaces payment)
  • x_payment — string — Optional: base64 X-PAYMENT header value (x402 exact scheme, USDC on Base mainnet). Omit it to receive the payment requirements (accepts[] + docs) for this call without being charged.
  • image_base64 — string — Base64-encoded image bytes (alternative to image_url)

  Hints: read-only no · 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.