# `com.mart402/docs` on anlyon.dev > Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX]. > No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour. - Page: https://anlyon.dev/servers/com.mart402/docs - JSON: https://anlyon.dev/api/v1/servers/com.mart402/docs - Version: 1.0.0 (active) - Publisher: com.mart402 (domain proven to the MCP Registry) - Runs: remote (streamable-http) - Sign-in to list tools: none - Metadata from the official MCP Registry, synced 2026-10-21T17:58:57.280Z Title and description, as the publisher wrote them: ```untrusted-server-text Documents and web for AI agents: PDF parse, OCR, web extract, invoice checks. x402, no API key. ``` Scanned 2026-10-21T18:52:04.219Z over streamable-http. **14 tools: 1 do something that can't be undone, 10 change things and 3 only read.** | Group | Class | Tools | Claude Code | | --- | --- | --- | --- | | Deletes or cancels | destructive | 0 | deny | | Can't be undone | irreversible | 1 | ask | | Changes things | write | 10 | ask | | Only reads | read | 3 | allow | ## Findings No check matched anything in these tool definitions. ## Can't be undone (1) Sends, pays, publishes or merges: once done, it cannot be taken back. Claude Code: ask. ### `pdf_merge` - The name "pdf_merge" says "merge": a word for a change that another call does not undo. Description, as the server wrote it: ```untrusted-server-text Merge 2-10 PDFs into one, in order. Deterministic, $0.003. ``` ## Changes things (10) Creates or changes something that can be changed back. Claude Code: ask. ### `document_pipeline` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `ocr_image` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `parse_document` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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_pages` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text Extract pages from a PDF by 1-based ranges (e.g. 1-3,7) into a new PDF. Deterministic, $0.002. ``` ### `quote_parse` - Nothing in its name or description says what it does, so it is counted as a write. - The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class. Description, as the server wrote it: ```untrusted-server-text 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). ``` ### `structured_extract` - The description's first verb is "fill": a word for a change. Description, as the server wrote it: ```untrusted-server-text 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. ``` ### `verify_invoice` - Nothing in its name or description says what it does, so it is counted as a write. Description, as the server wrote it: ```untrusted-server-text 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. ``` ## Only reads (3) Looks things up and changes nothing. Claude Code: allow. ### `get_catalog` - The name "get_catalog" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Mart402 product catalog: all products, prices, payment config, error codes, rate limits. Free. ``` ### `get_receipt` - The name "get_receipt" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text Re-fetch a previously paid result for free by receipt id (every paid response carries receipt_id). ``` ### `get_sample` - The name "get_sample" says "get": a word for reading. Description, as the server wrote it: ```untrusted-server-text 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. ``` ## Claude Code permissions For `.claude/settings.json`, assuming the server is installed as `docs`: ```json { "permissions": { "allow": [ "mcp__docs__get_catalog", "mcp__docs__get_receipt", "mcp__docs__get_sample" ], "ask": [ "mcp__docs__quote_parse", "mcp__docs__extract_url", "mcp__docs__parse_document", "mcp__docs__ocr_image", "mcp__docs__verify_invoice", "mcp__docs__enrich_company", "mcp__docs__structured_extract", "mcp__docs__document_pipeline", "mcp__docs__pdf_merge", "mcp__docs__pdf_pages", "mcp__docs__pdf_info" ], "deny": [] } } ```