com.mart402/docs

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

Documents and web for AI agents: PDF parse, OCR, web extract, invoice checks. x402, no API key.

Add to your agent

Copy this into your MCP client config:

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

Measured tools (14)

• 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

• quote_parse read-only

  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).

  Parameters:

  • url (required) — string — PDF URL

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

• 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

• extract_url

  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.

  Parameters:

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

• parse_document

  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.

  Parameters:

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

• ocr_image

  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.

  Parameters:

  • lang — string — One of: japanese, latin. Expected script for OCR: japanese or latin
  • 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)

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

• verify_invoice

  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.

  Parameters:

  • fields (required) — object — Extracted invoice fields: total_jpy, tax_jpy, reg_no, invoice_no, issue_date, due_date, vendor, customer
  • 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.
  • line_items — array — Optional line items [{description, amount_jpy}] to reconcile against the subtotal

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

• enrich_company

  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.

  Parameters:

  • company (required) — string — Company name, domain or URL
  • 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.
  • country_hint — string — ISO country hint for registry lookups, e.g. 'jp'

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

• structured_extract

  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.

  Parameters:

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

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

• document_pipeline

  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.

  Parameters:

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

• pdf_merge

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

  Parameters:

  • urls (required) — array — List of absolute PDF URLs, in order (2-10)
  • 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

• pdf_pages

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

  Parameters:

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

• pdf_info

  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.

  Parameters:

  • url (required) — string — Absolute http(s) URL of the input (web page or PDF, per tool)
  • 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

Publisher website

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