# @infoinlet/mcp-jp-doc-intel

Japanese document AI for agents — invoice & business-card extraction, OCR, classification (hosted API).

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.1.0
- **Author:** Unknown
- **License:** MIT
- **npm:** @infoinlet/mcp-jp-doc-intel
- **Source:** https://github.com/infoinlet-marketplace/marketplace
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 3 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-08-30T23:27:45.700Z
- **Version scanned:** 0.1.0
- **CVEs:** none found by OSV at scan time

## Tools

6 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `extract_invoice` — Extract structured fields from a Japanese (or English) invoice — vendor, invoice number, validated 適格請求書 T-number, dates (元号→Gregorian), subtotal/tax/total (zer
- `extract_document` — OCR/parse any document to text; optionally classify its Japanese document kind. Multi-page PDFs are split and processed page-by-page.
- `extract_handwriting` — VLM OCR for handwriting, hanko (stamps), and faxed/scanned artifacts. Returns recognized text.
- `extract_meishi` — Parse a business-card (meishi) image into name, kana, company, title, email, phone, and address. Give a local `path` or `content_base64`+`filename`.
- `classify_text` — Cheaply classify pasted text into a Japanese document kind (議事録/稟議書/仕様書/履歴書/契約書/請求書/始末書/generic). No file needed.
- `usage` — Show this API key’s usage/quota (trial keys show used/limit/remaining + expiry; subscribed keys are unlimited).

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp-jp-doc-intel\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@infoinlet/mcp-jp-doc-intel\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on your machine; read-only tool surface.
- Floor 13, ceiling 31 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40infoinlet%2Fmcp-jp-doc-intel
- Install plan: https://forgeregistry.com/api/v1/packages/%40infoinlet%2Fmcp-jp-doc-intel/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40infoinlet%2Fmcp-jp-doc-intel
- HTML page: https://forgeregistry.com/registry/%40infoinlet%2Fmcp-jp-doc-intel
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.