Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pdf-tables-mcp extract tables from this PDF of the Q3 earnings report"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Reliable PDF table extraction as an MCP tool. Drop into Claude, Cursor, or any MCP-compatible agent and get clean structured JSON tables back from any PDF — with per-cell citations to the source page.
Built by Tool Factory — Tool #2.
🚧 v0.1 scaffold — tools coming online over the next few days.
Agents drop a PDF URL, get back clean structured JSON tables with confidence scores and cell-level citations back to the source page.
Use cases:
RAG preprocessing: split tables from text-heavy docs
Agentic data extraction from financial filings, scientific papers, gov reports
Form-field reading in compliance workflows
Receipt/invoice line-item parsing
Related MCP server: document-parser
Tier | Price | Quota (pages/mo) |
Free | $0 | 50 pages |
Hobby | $19/mo | 250 pages |
Pro | $99/mo | 2,000 pages |
Business | $499/mo | 15,000 pages, 99.9% SLA |
Enterprise | Custom | Unlimited, VPC, SOC 2 path |
Quotas measure pages processed (not calls) — a 3-page PDF counts as 3 against your monthly quota. Keeps pricing fair for users running small and large PDFs alike.
{
"mcpServers": {
"pdf-tables": {
"url": "https://pdf-tables-mcp.vercel.app/api/mcp",
"headers": {
"Authorization": "Bearer pdt_live_YOURKEY"
}
}
}
}MIT
This server cannot be deployed
Extract tables, text and formulas from PDFs, including scanned pages and broken text layers.
PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.
Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.
High-fidelity PDF to structured Markdown conversion and document field extraction.