Techtenstein Pdf

io.github.sathvic-kolluPublished by GitHub account sathvic-kolluv1.0.2Updated Oct 24, 2026

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

VerifiedSTDIODesktop onlyFiles & StorageData & Analytics

Overview

AI-generated overview

A local MCP server that lets an assistant extract text, tables and metadata from PDF URLs, including scanned documents via OCR.

What you can do
Extract all text from a PDF URL as clean plain text, optionally using OCR for scanned documents. Extract tables as structured row arrays with page numbers. Read metadata such as title, author, page count, creation date and encryption status.
When to use it
Useful when you want an assistant to read PDFs found online — reports, invoices, earnings documents — and pull out their text, tables or basic metadata without downloading and parsing them yourself.
Requirements
Runs locally via uvx from the PyPI package techtenstein-pdf-mcp, configured in Claude Desktop, Cline or Cursor. Needs a TECHTENSTEIN_API_KEY environment variable from the provider's site; a free tier allows 50 extractions per day. Network access to the Techtenstein PDF Extract API and to the PDF URLs is required.
Before you install
The PDF URL and your API key are sent to the third-party Techtenstein API, so avoid confidential documents or private URLs. Paid tiers start at $5/month for 2,000 extractions; usage beyond the free daily quota may cost money. The key is stored in plain text in the client config file.

Installation

In SourceWeft

  1. Open Techtenstein Pdf in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Techtenstein PDF MCP

MCP server that gives your Claude, Cline, or Cursor session the ability to extract text, tables, and metadata from any PDF URL — including scanned PDFs via OCR. Powered by the Techtenstein PDF Extract API.

Tools exposed

  • pdf_extract_text(pdf_url, ocr=False) — Extract all text from a PDF as clean plain text
  • pdf_extract_tables(pdf_url) — Extract all tables as structured row arrays
  • pdf_metadata(pdf_url) — Get title, author, page count, creation date, encryption status

Install (Claude Desktop)

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "techtenstein-pdf": {      "command": "uvx",      "args": ["techtenstein-pdf-mcp"],      "env": {        "TECHTENSTEIN_API_KEY": "your_key_from_techtenstein.com"      }    }  }}

Restart Claude Desktop. pdf_extract_text, pdf_extract_tables, and pdf_metadata will appear as available tools.

Install (Cline / VS Code)

Cline auto-detects MCP servers from your Claude Desktop config. Same setup as above works.

Install (Cursor)

Add to ~/.cursor/mcp.json:

json
{  "mcpServers": {    "techtenstein-pdf": {      "command": "uvx",      "args": ["techtenstein-pdf-mcp"],      "env": {"TECHTENSTEIN_API_KEY": "your_key"}    }  }}

Get an API key

Free tier (50 extractions/day, no card): https://apis.techtenstein.com

Paid tiers start at $5/month for 2,000 extractions.

Example usage

Once installed, ask Claude:

"Extract the tables from this earnings report PDF: https://example.com/q4.pdf"

Claude will call pdf_extract_tables and return a clean structured view of every table on the page.

Or for scanned documents:

"This PDF is a scanned invoice. Extract the text: https://example.com/invoice.pdf"

Claude will call pdf_extract_text(pdf_url, ocr=True) and read the image-based text via OCR.

Response schema (text mode)

json
{  "text": "Full extracted body text...",  "page_count": 12,  "word_count": 3450,  "ms": 240}

Response schema (tables mode)

json
{  "tables": [    {      "page": 3,      "rows": [        ["Product", "Q1", "Q2", "Q3", "Q4"],        ["Widget A", "1200", "1350", "1420", "1600"]      ]    }  ]}

Support

License

MIT

Source: README.md at commit 4cc1ccb

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.