Pdf Extract MCP tool

Network tool

MCP findutils:pdf_extract

PDF Text Extractor. Extract text and structured JSON (with bounding boxes) from a PDF. Accepts either a public https:// URL pointing to a PDF, or a base64-encoded PDF string. Runs entirely on Cloudflare Workers via WebAssembly — the bytes are not logged. Best for documents under 10MB.

Try it

Arguments

application/json

pdf

string required

PDF as a base64-encoded string (with or without data: prefix) OR a public https:// URL pointing to a PDF.
output

string optional

What to return: layout-preserved text, structured JSON, or both. One of text · json · all.
maxPages

integer optional

Hard cap on pages parsed. Helps bound CPU time on huge documents.

Example arguments

Verified

{
  "pdf": "https://findutils.com/docs/sample.pdf",
  "output": "text",
  "maxPages": 1
}

claude mcp add findutils --transport http https://mcp.findutils.com/

{
  "mcpServers": {
    "findutils": {
      "url": "https://mcp.findutils.com/"
    }
  }
}

curl -X POST https://mcp.findutils.com/ \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "pdf_extract",
      "arguments": {
        "pdf": "https://findutils.com/docs/sample.pdf",
        "output": "text",
        "maxPages": 1
      }
    }
  }'

Also a REST endpoint

The same tool answers plain HTTP at POST /api/tools/pdf-extract/execute.

REST reference

Rate limit: 120 a minute, per IP
Auth: None
REST id: pdf-extract
MCP name: pdf_extract
Category: Developer
Machine-readable: openapi.json · markdown.md

This tool fetches a fixed, hard-coded public upstream, never a private host. Results depend on that upstream.

Arguments

Example arguments

More Developer tools

More to explore