com.mart402/docs

Est-ce que com.mart402/docs est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.mart402/docs » 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 14 outils

• document_pipeline≈ 431 tokens

  One call: PDF invoice to parse (hallucination-guarded OCR) + field extraction + arithmetic verification (+optional issuer enrich). Flat $0.05/document; inputs validated before payment. Choose this when a PDF is an invoice/receipt and you want parse + field extraction + arithmetic verification in one paid call; for text only use parse_document.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    Absolute http(s) URL of the input (web page or PDF, per tool)
  • enrich · boolean · optionnel
    Also run issuer enrichment on the parsed invoice
  • x_payment · string · optionnel
    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.

  Exemple d'appel

  {"name": "document_pipeline", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• enrich_company≈ 433 tokens

  Company name/domain/URL to a verified profile from primary sources + GLEIF LEI and Japan NTA corporate-number registries. Per-field evidence + confidence, honest nulls; unresolved lookups never charged. $0.03/company. Choose this when you have a company NAME or DOMAIN and need a registry-grounded profile (GLEIF LEI / Japan NTA) with per-field evidence; pass country_hint 'jp' for Japanese companies.

  Paramètres, retour & exemple (3)

  Paramètres

  • company · string · requis
    Company name, domain or URL
  • x_payment · string · optionnel
    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.
  • country_hint · string · optionnel
    ISO country hint for registry lookups, e.g. 'jp'

  Exemple d'appel

  {"name": "enrich_company", "arguments": {"company": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• extract_url≈ 452 tokens

  Extract a web page to clean Markdown + metadata (auto JS rendering, robots.txt respected). $0.005 fast / $0.01 rendered; cached results half price. Choose this when you need a web PAGE as clean Markdown to read yourself; to fill a schema use structured_extract, for a PDF use pdf_info then parse_document.

  Paramètres, retour & exemple (4)

  Paramètres

  • ttl · integer · optionnel
    cache seconds (0 = no cache)
  • url · string · requis
    Absolute http(s) URL of the input (web page or PDF, per tool)
  • mode · string · optionnel · auto | fast | heavy
    Extraction mode: auto (fast with rendered fallback), fast, heavy
  • x_payment · string · optionnel
    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.

  Exemple d'appel

  {"name": "extract_url", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• get_catalog≈ 261 tokens

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

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_catalog", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• get_receipt≈ 287 tokens

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

  Paramètres, retour & exemple (1)

  Paramètres

  • receipt_id · string · requis
    receipt_id from a paid response (rcpt_...)

  Exemple d'appel

  {"name": "get_receipt", "arguments": {"receipt_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• get_sample≈ 609 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • product · string · requis · document-pipeline | enrich | extract | jp-bonus-net | jp-business-days | jp-company | jp-consumption-tax | jp-crypto-tax
    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)

  Exemple d'appel

  {"name": "get_sample", "arguments": {"product": "document-pipeline"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• ocr_image≈ 448 tokens

  OCR one image to text with dual-engine consensus, calibrated confidence and per-segment corroboration. Japanese-strong. Flat $0.05/image. Choose this when the input is an IMAGE (photo, screenshot, receipt); for PDFs use parse_document.

  Paramètres, retour & exemple (4)

  Paramètres

  • lang · string · optionnel · japanese | latin
    One of: japanese, latin. Expected script for OCR: japanese or latin
  • image_url · string · optionnel
    Absolute http(s) URL of the image (JPEG/PNG/WebP)
  • x_payment · string · optionnel
    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 · optionnel
    Base64-encoded image bytes (alternative to image_url)

  Exemple d'appel

  {"name": "ocr_image", "arguments": {"lang": "japanese", "image_url": "texte", "x_payment": "texte", "image_base64": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• parse_document≈ 462 tokens

  Parse a PDF to structured Markdown (hallucination-guarded OCR for scanned pages, Japanese-strong). Pass url (one step: the 402 quotes the exact price for that PDF) or quote_id from quote_parse (price fixed by the quote). One of the two is required. Choose this when the input is a PDF and you want its full text as Markdown; call pdf_info first if you do not know whether it is scanned, and use document_pipeline instead for invoices you also want verified.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · optionnel
    Absolute http(s) URL of the PDF (one-step form)
  • quote_id · string · optionnel
    quote_id returned by quote_parse (price is fixed by the quote)
  • x_payment · string · optionnel
    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.

  Exemple d'appel

  {"name": "parse_document", "arguments": {"url": "texte", "quote_id": "texte", "x_payment": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• pdf_info≈ 364 tokens

  PDF facts before you pay for parsing: pages, metadata, per-page text volume, scanned-or-not estimate. $0.001. Choose this first for any unknown PDF (cheapest real call); then parse_document, pdf_pages or document_pipeline.

  Paramètres, retour & exemple (2)

  Paramètres

  • url · string · requis
    Absolute http(s) URL of the input (web page or PDF, per tool)
  • x_payment · string · optionnel
    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.

  Exemple d'appel

  {"name": "pdf_info", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• pdf_merge≈ 327 tokens

  Merge 2-10 PDFs into one, in order. Deterministic, $0.003.

  Paramètres, retour & exemple (2)

  Paramètres

  • urls · array · requis
    List of absolute PDF URLs, in order (2-10)
  • x_payment · string · optionnel
    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.

  Exemple d'appel

  {"name": "pdf_merge", "arguments": {"urls": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• pdf_pages≈ 356 tokens

  Extract pages from a PDF by 1-based ranges (e.g. 1-3,7) into a new PDF. Deterministic, $0.002.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    Absolute http(s) URL of the input (web page or PDF, per tool)
  • pages · string · requis
    1-based page ranges, e.g. '1-3,7'
  • x_payment · string · optionnel
    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.

  Exemple d'appel

  {"name": "pdf_pages", "arguments": {"url": "texte", "pages": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• quote_parse≈ 296 tokens

  Free quote for PDF parsing: page count, route (text/scan-OCR) and the exact final price, before any payment. Use the returned quote_id with parse_document (on /mcp or /mcp/docs).

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    PDF URL

  Exemple d'appel

  {"name": "quote_parse", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• structured_extract≈ 419 tokens

  Fill YOUR JSON schema from any URL (hybrid LLM + deterministic canonicalization). $0.03/call. Choose this when you have your OWN JSON schema to fill from any page; for company profiles use enrich_company or jp_company_profile.

  Paramètres, retour & exemple (4)

  Paramètres

  • url · string · requis
    Absolute http(s) URL of the input (web page or PDF, per tool)
  • schema · object · requis
    {key: description} pairs
  • x_payment · string · optionnel
    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.
  • instructions · string · optionnel
    optional extra guidance for filling the schema

  Exemple d'appel

  {"name": "structured_extract", "arguments": {"url": "texte", "schema": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

• verify_invoice≈ 450 tokens

  Verify extracted invoice fields: arithmetic consistency, line-item totals, JP registration number check-digit + corporate-number existence observation (official Japan NTA registry), accounting-ready JSON. $0.015/call. Choose this when you already HAVE invoice fields (from your own extraction) and only need them checked; to start from a PDF use document_pipeline.

  Paramètres, retour & exemple (3)

  Paramètres

  • fields · object · requis
    Extracted invoice fields: total_jpy, tax_jpy, reg_no, invoice_no, issue_date, due_date, vendor, customer
  • x_payment · string · optionnel
    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.
  • line_items · array · optionnel
    Optional line items [{description, amount_jpy}] to reconcile against the subtotal

  Exemple d'appel

  {"name": "verify_invoice", "arguments": {"fields": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"body": "texte", "status": 1, "how_to_pay": "texte", "receipt_id": "texte", "payment_required": true}}

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://mart402.com/mcp/docs