Drops a PDF URL into Claude or any MCP client and returns structured JSON tables with per-cell citations back to the source page. Built for RAG preprocessing, financial filings, invoice parsing, or anywhere you need clean tabular data extracted from documents without manual copy-paste. Uses a page-based quota system instead of per-call metering, so a 10-page PDF counts as 10 pages against your monthly limit. Currently in v0.1 scaffold with tools rolling out. Free tier gives you 50 pages monthly, paid plans scale to 15k pages with SLA at the business level. Connects via streamable HTTP transport with bearer token auth.
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:
| 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
csoai-org/pdf-document-mcp
xt765/mcp-document-converter
io.github.ai-aviate/better-notion
suekou/mcp-notion-server
meterlong/mcp-doc
n24q02m/better-notion-mcp