Techtenstein PDF MCP Server

by sathvic-kollu Your server? Claim it

local only

Techtenstein PDF runs on your own machine — the client starts it, so there is no endpoint to ping. 59 installs a week from pypi. Last commit 13 Jul 2026.

PDF text and table extraction plus metadata. Supports OCR for scanned documents.

Installs per day peak 23 · avg 10 · -22% w/w

a month agotoday

Installs / week

pypi · techtenstein-pdf-mcp

Stars

0 open issues

13 Jul 2026

Last commit

0 releases in 90 days

—

License

Python

Nothing serious here today

Today is the operative word: we check Techtenstein PDF 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 techtenstein-pdf -- uvx techtenstein-pdf-mcp

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

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

~/.codex/config.toml

[mcp_servers.techtenstein-pdf]
command = "uvx"
args = ["techtenstein-pdf-mcp"]

.cursor/mcp.json

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

.vscode/mcp.json

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

This one needs environment variables set before it will start: TECHTENSTEIN_API_KEY (API key from https://apis.techtenstein.com (free tier: 50 extractions/day)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Techtenstein PDF

same job, measured the same way

PDF Text, Table and OCR Extractor

by brenton-keller

PDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.

answering

Rq Scan

by recerqa

MCP Server for RQ-SCAN - AI-powered document OCR and data extraction platform

21 installs/wk local only

Docu-Scan MCP

by spocont

PDF and document extraction via Google Document AI. Free trial available.

answering

Document Processing

by filegraph

Extract text from documents, manipulate PDFs, and perform OCR on images.

9 tools answering

PDF Reader

by xvvln

MCP server for extracting text, images, tables, links, annotations, and metadata from PDF files.

85 installs/wk local only

PDF MCP

by wesseltl

Extract text and tables from PDFs for an agent: invoices, reports, statements.

109 installs/wk local only

Pdfco

by mcparmory

Extract data, edit, convert, and parse PDF documents with OCR and AI

239 installs/wk local only

Suparse Document Processing

by suparse

Extract structured data from PDFs and documents with Suparse AI OCR.

132 installs/wk local only

Techtenstein PDF — questions

Answers built from our own checks of this server.

Why is there no uptime for Techtenstein PDF?

Techtenstein PDF 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 techtenstein-pdf-mcp was installed 59 times last week.

How do I connect Techtenstein PDF?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls techtenstein-pdf-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Techtenstein PDF?

The pypi package techtenstein-pdf-mcp was installed 59 times in the last week. Week over week that is -22%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Techtenstein PDF open source?

We cannot say either way: written in Python and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.