# com.mart402/extract

> Web extraction, OCR (Japanese-strong), invoice and company data for AI agents. x402, no API key.

- name: com.mart402/extract
- version: 0.2.0
- connection class: R0 (autonomous)
- trust: 79/100 flags: no-repository
- quality: 81/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.mart402%2Fextract
- tools: https://api.protogrid.dev/v1/servers/com.mart402%2Fextract/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "extract": {
      "type": "http",
      "url": "https://mart402.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 97
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-94% ~updated-81d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 35 of 35 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- warn `tools.token_cost`: about 9,329 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 117 tool changes in 30 days
- fail `stability.rug_pull`: 3 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 35, about 9,329 tokens to load them all
- tool set hash: 16950791c194d39ca026cb20790469f5
- tools last changed: 2026-10-20T06:25:54.674Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.mart402/extract.svg)](https://protogrid.dev/servers/com.mart402/extract)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `operator_history` changed (title, annotations)
- 2026-10-20 `portrait_precheck` changed (title, annotations)
- 2026-10-20 `get_sample` changed (title, annotations)
- 2026-10-20 `search_x402_services` changed (title, annotations)
- 2026-10-20 `get_receipt` changed (title, annotations)
- 2026-10-20 `quote_parse` changed (title, annotations)
- 2026-10-20 `get_catalog` changed (title, annotations)
- 2026-10-19 `jp_payroll_suite` changed (outputSchema)
- 2026-10-19 `jp_crypto_tax` changed (outputSchema)
- 2026-10-19 `jp_payslip_audit` changed (inputSchema, outputSchema)

Full history: https://api.protogrid.dev/v1/servers/com.mart402%2Fextract/changes

## Remotes

- https://mart402.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9369369)

## Packages

_none_

## Tools (35)

- `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.
- `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.
- `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.
- `get_catalog`: Mart402 product catalog: all products, prices, payment config, error codes, rate limits. Free.
- `get_receipt`: Re-fetch a previously paid result for free by receipt id (every paid response carries receipt_id).
- `get_sample`: 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.
- `jp_bonus_net`: Bonus net pay: social insurance and withholding tax (official rate table, based on previous month salary). $0.01/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_business_days`: Japanese holidays, business-day arithmetic, statutory filing deadlines with holiday shift, wareki conversion. $0.003/call. Deterministic, cites primary sources; errors and unverified rules are never billed. Required by mode (default add): add -> from, days; between -> from, to; holidays -> year; deadline -> kind, base_date; wareki -> date.
- `jp_company_profile`: Japanese company site to a standard profile JSON (name, address, representative, capital, contact). $0.03/site. Choose this when you have the URL of a Japanese company's OWN site and want its standard profile fields read from the page; for name/domain lookups use enrich_company (country_hint: jp).
- `jp_consumption_tax`: Consumption tax: per-rate invoice rounding, qualified-invoice validation, simplified taxation, 20% special. $0.01/call. Deterministic, cites primary sources; errors and unverified rules are never billed. Required by mode (default invoice_totals): invoice_totals -> lines; validate_invoice -> document; simplified -> taxable_sales_excl_yen, category; two_percent -> taxable_sales_excl_yen, taxable_period_start, taxable_period_end.
- `jp_crypto_tax`: Japan crypto-asset tax: realized income under the NTA total-average or moving-average method (sell/spend/exchange as disposals, fees deductible), verified against the official NTA FAQ examples. $0.05/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_dependent_threshold`: Income-wall analysis: tax, social insurance (1.06M/1.30M), spousal and student-dependent walls. $0.02/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_mortgage`: Mortgage schedules (level payment/principal), total interest, prepayment effect. $0.005/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_overtime_wage`: Overtime premium pay (Labor Standards Act Art.37, official rounding notice) and Article-36 limit check. $0.015/call. Deterministic, cites primary sources; errors and unverified rules are never billed. Required by mode (default pay): pay -> monthly_salary_yen, monthly_scheduled_hours, hours; check36 -> monthly_overtime_hours.
- `jp_payroll_net`: Annual gross salary to net take-home (social insurance + income tax + resident tax). Exact NTA Beppyo-5 table. $0.02/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_payroll_suite`: Japan payroll suite: net salary + social insurance + income walls (+bonus) in one call. Flat $0.05.
- `jp_payslip_audit`: Audit a Japanese payslip: recompute statutory premiums and withholding tax from official tables and diff against the actual amounts, with per-item verdicts (match/explainable/mismatch). $0.02/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_retirement_tax`: Retirement income tax: deduction by years of service, half-taxation rules, exact withholding rounding. $0.02/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `jp_social_insurance`: Monthly social insurance premiums from the official Kyokai-Kenpo grade table (FY2026). $0.01/call. Deterministic, cites primary sources; errors and unverified rules are never billed.
- `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.
- `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.
- `operator_history`: Free 12-week measured score history for any x402 operator from the Market402 index (weekly series, trend, volatility, badge). Check a seller's record before your agent pays an unfamiliar endpoint.
- `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.
- `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.
- `pdf_merge`: Merge 2-10 PDFs into one, in order. Deterministic, $0.003.
- `pdf_pages`: Extract pages from a PDF by 1-based ranges (e.g. 1-3,7) into a new PDF. Deterministic, $0.002.
- `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.
- `portrait_precheck`: 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.
- `quote_parse`: 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).
- `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.
- `search_x402_services`: Search the Market402 verified index of the whole x402 economy by capability (e.g. 'ocr', 'market-data'). Every result is a real, probed resource with a measured 402 Score. Free.
- `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.
- `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.
- `style_report`: Client-ready deliverable: the style-profile analysis rendered as a finished English PDF report (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).
- `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.