Techtenstein PDF MCP Server
MCP server that enables a Claude, Cline, or Cursor session to extract text, tables, and metadata from any PDF URL. It supports OCR for scanned PDFs, using the Techtenstein PDF Extract API to process the document content and return results via exposed MCP tools.
🛠️ Key Features
- PDF text extraction as clean plain text
- Table extraction as structured row arrays
- Metadata extraction (e.g., title, author, page count, creation date, encryption status)
- OCR support for scanned PDFs via
pdf_extract_text(pdf_url, ocr=False)
🚀 Use Cases
- Extracting searchable text from PDF URLs
- Converting PDF table content into structured row data
- Retrieving document metadata for indexing or downstream processing
⚡ Developer Benefits
- Tool-based access to
pdf_extract_text,pdf_extract_tables, andpdf_metadata - Optional OCR toggle for text extraction workflows involving scanned documents
⚠️ Limitations
- OCR functionality is only described for text extraction (
ocr=Falseparameter) and is not specified for table extraction or metadata extraction.