PDFluent MCP server

pdfluent-mcp

<!-- mcp-name: io.github.pdfluent/pdfluent-mcp -->

An MCP server for PDFluent. It lets Claude Desktop, Claude Code, Cursor, VS Code and any other MCP client read a local PDF as markdown, plain text, tables or positioned blocks, look up its metadata, search it, and fill its form fields into a new file.

It runs over stdio, one process per client, on the pdfluent Python package. Your documents stay on your machine. The server reads and writes only inside the directories you allow. The balanced quality tier needs model files; pdfluent models install downloads them once. Your documents are never uploaded.

<!-- TODO: demo GIF (Claude Desktop asking for the tables of a local PDF). -->

Tools

Page numbers are 0-based in every argument and result. confidence is the probability of the learned model that decided a block's kind; it is null where no model decided it, and null means unknown, not low.

Install

Needs Python 3.10 or later and uv. uvx downloads the server and pdfluent on first use and caches them.

uvx pdfluent-mcp --root ~/Documents

Or into an environment of your own:

pip install pdfluent-mcp
pdfluent-mcp --root ~/Documents

Allowed roots

The server touches nothing outside its roots. Give them with --root (repeat for more than one), with PDFLUENTMCPROOTS (:-separated, ; on Windows), or let the client offer them: Claude Code sends its working directory and --add-dir directories as MCP roots. A server with no root from any of these answers every call with a message saying so. Symlinks are resolved before the check, so a link inside a root cannot point outside it.

A root is as wide as the directory it names. A client that offers /, ~ or a drive as an MCP root widens the server to everything the user can read; if that is not what you want, start the server with --root on the folder your PDFs live in and keep the client's roots narrow.

Shortened. The full README is on GitHub.