pdfmux

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nameetp-pdfmux

About

Use cases: document-processing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

9 read · 0 write · 0 deleteRead-only

Secrets

1 (API keys, tokens or passwords)

Install scripts

None found

Runs as

Python package

Tools (9)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• analyze_pdf

  Quick PDF triage — classify type and audit page quality without full extraction. Returns page count, type detection, per-page quality breakdown, and estimated extraction difficulty. Much cheaper than convert_pdf for initial assessment.

• batch_convert

  Convert all PDFs in a directory to Markdown. Returns a summary with per-file results.

• convert_pdf

  Convert a PDF to AI-readable Markdown. Automatically detects the PDF type and picks the best extraction method. Returns confidence score and warnings when extraction is limited.

• extract_pdf

  Convert a PDF to AI-readable Markdown. Auto-detects the document type (digital, scanned, or mixed) and picks the best extraction method. When the result is uncertain — a low-confidence page, an image-only scan, or a partial extraction — a short header is prepended with the confidence score, the extractor used, and any warnings, so you can decide whether to trust the text rather than silently ingesting a bad extraction. Args: file_path: Absolute path to the PDF file to extract. quality: "fast" (native text only, no OCR — cheapest), "standard" (native text + OCR fallback on ima…

• extract_streaming

  Stream extraction events for a PDF as NDJSON. Use for large documents (100+ pages) where waiting for the full extraction is impractical. The response body is newline-delimited JSON with one object per line: {"type":"classified","data":{"page_count":N,"page_types":[...]}} {"type":"page","data":{"page_num":0,"text":"...","confidence":0.92,...}} {"type":"warning","data":{"message":"..."}} (zero or more) {"type":"complete","data":{"total_confidence":0.94,"ocr_pages":[...],...}} The first event is always ``classified``; the last is always ``complete``. Each ``page`` event …

• extract_structured

  Extract structured data from a PDF — tables as JSON, key-value pairs, and optionally map to a JSON schema. Returns tables with headers/rows, detected key-value pairs with auto-normalization (dates, amounts, rates), and schema-mapped output if a schema is provided.

• extract_tables

  Use this when the user uploads or links a PDF and says 'convert this PDF to Excel', 'bank statement to spreadsheet', 'extract the table from this PDF' or 'PDF to CSV', or asks whether every row came through. Pulls every table out of the PDF, joins tables that continue across pages, keeps numbers as numbers, and when the table has a running balance checks each row against it so a skipped line shows up. Returns CSV and an Excel download link. Reads up to 30 pages and 25 MB. Do not use for editing, signing or creating PDFs, or for images that are not PDFs.

• get_pdf_metadata

  Get PDF metadata instantly — page count, file size, document type, and whether it has tables. No extraction performed. Use this first to decide which tool to call next: convert_pdf for full text, analyze_pdf for quality audit, or extract_structured for tables.

• verify_extraction

  Audit an extraction of a PDF for silently-dropped pages — the failure where an extractor returns nothing for a page that has real text while reporting success. Pass extracted_text with another engine's output (Reducto, Mistral OCR, LlamaParse, Docling, an in-house parser — as JSON, Markdown, or plain text) to certify THAT engine against the source PDF; omit it to have pdfmux extract the document itself and certify its own read. Returns the per-page audit — each page marked usable / silently-empty / recovered / review / unverifiable — the "N of M pages silently dropped" headline, and an overall…

Signals

Stars

84

Forks

14

Open issues

3

Contributors

6

Weekly downloads

145

Last commit

Oct 16, 2026 (12 days ago)

Last release

Jul 27, 2026 (3 months ago)

Last package publish

Jul 27, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.NameetP/pdfmux

Version

1.8.7

Auth

API key

Packages

pypi pdfmux

License

MIT

Repository

github.com/NameetP/pdfmux

Website

pdfmux.com

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql