Skip to content
mcp/skillhub

pdfmux MCP Server

by nameetpio.github.NameetP/pdfmuxv1.8.7

PDF extraction router that classifies each page and routes it to PyMuPDF, Docling, OCR or an LLM fallback, re-extracting pages with low confidence scores.

83Pythonstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active2d ago

Install pdfmux MCP server

Install in Claude Code

claude mcp add pdfmux -e GEMINI_API_KEY='<gemini-api-key>' -- uvx pdfmux

Configuration

VariableRequiredSecretDescription
GEMINI_API_KEY—yesOptional Google AI API key. Enables the paid Gemini Flash fallback for pages where all local backends report low confidence. pdfmux runs 100% locally without this.

Freshness

Active — last maintenance signal 2d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-10-08 · 2d ago · GitHub

  2. Latest release

    2026-07-27 · 2mo ago · GitHub · v1.8.7

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-07-27 · 2mo ago · official registry · v1.8.7

FAQ

›How do I install the pdfmux MCP server in Claude Code?

Run: claude mcp add pdfmux -e GEMINI_API_KEY='<gemini-api-key>' -- uvx pdfmux. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does pdfmux require an API key?

Yes. It expects GEMINI_API_KEY, of which 1 is a secret.

›Can I use pdfmux as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is pdfmux in the official MCP registry?

Yes, as io.github.NameetP/pdfmux.

Alternatives to pdfmux

Other web search MCP servers.

View all