PDFluent MCP Server

by pdfluent Your server? Claim it

local only

PDFluent runs on your own machine — the client starts it, so there is no endpoint to ping. 361 installs a week from pypi. Last commit 23 Oct 2026.

Read, search and fill PDFs as markdown, text, tables, forms. Your documents stay on your machine.

Installs per day peak 263 · avg 12

a month agotoday

361

Installs / week

pypi · pdfluent-mcp

Stars

0 open issues

23 Oct 2026

Last commit

from GitHub

AGPL-3.0

License

Python

Nothing serious here today

Today is the operative word: we check PDFluent every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add pdfluent-mcp -- uvx pdfluent-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pdfluent-mcp": {
      "command": "uvx",
      "args": [
        "pdfluent-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.pdfluent-mcp]
command = "uvx"
args = ["pdfluent-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "pdfluent-mcp": {
      "command": "uvx",
      "args": [
        "pdfluent-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "pdfluent-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pdfluent-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: PDFLUENT_MCP_MAX_PAGES (Pages one call may read (default 200)), PDFLUENT_MCP_MAX_BYTES (Largest document the server opens, in bytes (default 104857600)), PDFLUENT_MCP_MAX_OUTPUT_CHARS (Longest result one call returns, in characters (default 200000)).

Alternatives to PDFluent

same job, measured the same way

FATSEARCH

by fatsearch

Web pages, PDFs and documents as small, clean, cached Markdown for AI agents

local only

ELO ECM

by herzog-gmbh

ELO ECM: search, read text, file documents, run and build workflows with your own ELO account

local only

Membase

by membase

Long-term memory for you and your AIs: search memories, read the profile, add facts and documents.

answering

Lupa — local file search for your Mac

by under71

Search your Mac's files by name and by text inside documents. Local index, Korean-aware.

16 installs/wk local only

Lupa — local file search for your Mac

by paeyoungpark-web

Search your Mac's files by name and by text inside documents. Local index, Korean-aware.

local only

MyMemory

by mymemory

Long-term memory for AI assistants: search, read and save your notes, links and documents.

295 installs/wk answering

reMarkable MCP Server

by wavyrai

Access your reMarkable tablet - read documents, browse files, extract text and OCR handwritten notes

361 installs/wk local only

docx4j Word documents

by plutext

Read, convert and fill Word (.docx) documents: templates, Markdown/HTML in and out, PDF with math.

local only

PDFluent — questions

Answers built from our own checks of this server.

Why is there no uptime for PDFluent?

PDFluent runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package pdfluent-mcp was installed 361 times last week.

How do I connect PDFluent?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls pdfluent-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use PDFluent?

The pypi package pdfluent-mcp was installed 361 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is PDFluent open source?

Yes — it is published under the AGPL-3.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.