pdfmux

About this integration

PDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.

Transport

stdio

Authentication

none

Initial setup

none

Runtime

unattended

Evidence

documented

Version

1.8.7

Package

pdfmux

Last compatibility test

Not independently tested

Connect your agent

Publisher documentation and the Python manifest were reviewed without importing, installing, or executing the package. Qualification is limited to the manifest-declared Python pdfmux console entry point in documented local stdio mode and local rule-based extraction. Optional HTTP serving and BYOK cloud/LLM providers, including their credentials, costs, retries, and data handling, are outside this approval. The README's separate npx pdfmux-mcp example was not used as connection proof for this Python artifact. Documented status is not a runtime, extraction-quality, or security test.

Capabilities: Extract text and structured data from local PDF files, Audit extraction output for missing pages, Read PDF metadata, Batch-convert local PDF files

Connected profiles

Additional details