mcpbeat

Extract MCP Server

com.mart402/extract
answering

Extract is answering right now. Last checked 12 min ago. It exposes 15 tools.

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

Uptime history 39 hours of history
39 hours agonow
100.0%
Uptime 24h
91 of 91 checks
15
Tools
read from the server
398 ms
Response time
average over 24h
open, no key
Access
streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

run in your terminal
claude mcp add extract --transport http https://mart402.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "extract": {
      "url": "https://mart402.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.extract]
url = "https://mart402.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "extract": {
      "url": "https://mart402.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "extract": {
      "url": "https://mart402.com/mcp"
    }
  }
}

Available tools 15

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

pdf
pdf_info
PDF facts before you pay for parsing: pages, metadata, per-page text volume, scanned-or-not estimate. $0.001.
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.
catalog
get_catalog
Mart402 product catalog: all products, prices, payment config, error codes, rate limits. Free.
company
jp_company_profile
Japanese company site to a standard profile JSON (name, address, representative, capital, contact). $0.02/site.
document
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.
enrich
enrich_company
Company name/domain/URL to a verified profile from primary sources + GLEIF LEI registry. Per-field evidence + confidence, honest nulls; unresolved lookups never charged. $0.015/company.
extract
extract_url
Extract a web page to clean Markdown + metadata (auto JS rendering, robots.txt respected). $0.003 fast / $0.006 rendered; cached results half price.
ocr
ocr_image
OCR one image to text with dual-engine consensus, calibrated confidence and per-segment corroboration. Japanese-strong. Flat $0.005/image.
parse
parse_document
Parse a quoted PDF to structured Markdown (hallucination-guarded OCR for scanned pages, Japanese-strong). Get quote_id from quote_parse first; price is fixed by the quote.
quote
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.
receipt
get_receipt
Re-fetch a previously paid result for free by receipt id (every paid response carries receipt_id).
structured
structured_extract
Fill YOUR JSON schema from any URL (hybrid LLM + deterministic canonicalization). $0.02/call.
verify
verify_invoice
Verify extracted invoice fields: arithmetic consistency, line-item totals, accounting-ready JSON. $0.005/call.
x402
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.

Endpoints

URLTransportStateLatencyChecked
https://mart402.com/mcp streamable-http answering 438 ms 12 min ago

Extract — questions

Answers built from our own checks of this server.

What can Extract do?
It exposes 15 tools, read directly from the server on our last check. Among them: document_pipeline, enrich_company, extract_url, get_catalog, get_receipt, jp_company_profile and 9 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Extract working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 398 ms. The bar chart above shows every period we have measured.
How do I connect Extract?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Extract need an API key?
No. Extract completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 15 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Extract?
It answers our handshake in 398 ms on average, which is faster than 34% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.