PDF To Text

io.github.Jim-Panse/pdf-to-text

Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry.

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "pdf-to-text": {
      "command": "npx",
      "args": [
        "-y",
        "@jim-panse/pdf-to-text-mcp@0.7.0"
      ],
      "env": {
        "PDF_TO_TEXT_MCP_ROOT": "<your PDF_TO_TEXT_MCP_ROOT>",
        "OPENAI_API_KEY": "<your OPENAI_API_KEY>",
        "AI_MAX_OUTPUT_TOKENS": "32000",
        "EXTRACTION_QUEUE_CAPACITY": "10",
        "EXTRACTION_QUEUE_WAIT_MS": "60000",
        "WRITE_TEXT": "false"
      }
    }
  }
}
Environment variables
  • PDF_TO_TEXT_MCP_ROOTrequiredRequired existing directory that defines the root-relative filesystem namespace for PDF input and derived text output.
  • OPENAI_API_KEYsecretOptional secret. Enables one AI extraction retry when local extraction is inadequate; omit for local-only operation.
  • AI_MAX_OUTPUT_TOKENSOptional cap for all AI-generated output tokens, including non-visible reasoning tokens. Integer minimum 800; defaults to 32000.
  • EXTRACTION_QUEUE_CAPACITYInteger maximum waiting requests from 0 to 100; zero disables waiting.
  • EXTRACTION_QUEUE_WAIT_MSMaximum queue wait in milliseconds, integer 1 through 2147483647. Does not limit active work.
  • WRITE_TEXTOptionally save successful extraction text beside the source PDF.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Developer Tools
Version
0.7.0
Registry
active
Published
10/15/2026
Browse all Developer Tools →

Add the badge to your site

Show visitors that PDF To Text is listed here — it’s also the link we check for a free listing.

PDF To Text — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-jim-panse-pdf-to-text?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="PDF To Text — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![PDF To Text — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-jim-panse-pdf-to-text?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.