thinkpdf 1.0.5

PDF to Markdown engine for LLMs. Smart table extraction, OCR, MCP server.

thinkpdf

Extract text, tables, and structure from PDFs. Built for RAG pipelines, AI training, and LLM context.

Read directly into memory or save as Markdown. Supports OCR.

Install

pip install thinkpdf        # Python (PyPI)
npx thinkpdf                 # npm (run directly)
brew install thinkpdf        # macOS (Homebrew)
choco install thinkpdf       # Windows (Chocolatey)
snap install thinkpdf        # Linux (Snap Store)
conda install -c conda-forge thinkpdf  # Anaconda (pending)

For better table extraction (but slower):

pip install thinkpdf[docling]

Quick Start

thinkpdf document.pdf                # outputs document.md
thinkpdf document.pdf -o output.md   # custom output
thinkpdf folder/ --batch             # convert all PDFs

from thinkpdf import convert
convert("document.pdf")  # returns markdown

GUI

pip install thinkpdf[gui]
thinkpdf-gui

MCP Server

Add to your MCP config:

{
  "mcpServers": {
    "thinkpdf": {
      "command": "python",
      "args": ["-m", "thinkpdf.mcp_server"]
    }
  }
}

Tool	Description
read_pdf	Read PDF content into context
convert_pdf	Convert and save to file
get_document_info	Get PDF metadata

License

AGPL-3.0