io.github.PyJudge/pdf4vllmmedia

pdf4vllm

Stale · 9 mo silent

PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.

Install

claude mcp add pdf4vllm -- uvx pdf4vllm-mcp

Our take

This server is a PDF ingestion tool for vision-capable language models, with logic to detect text corruption and fall back to image-based handling. It is for LLM pipeline builders who need more resilient document input than plain text extraction provides. The problem it addresses is real and specific, but the package appears early-stage from this listing and its quality will depend heavily on how well that fallback logic performs in practice.

reviewed by hand · 2026-07-22

Something wrong or dead here? Report it

Verification record

last verified
23 days ago
github stars
0
last commit
9 mo ago
archived
no
license
NOASSERTION
in registry since
2025-12-02

github.com/PyJudge/pdf4vllm-mcp

More in media

browse all →
funasr-mcpmedia

FunASR

Verified · 20 days ago

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

hand-reviewed20k starschecked 20 days ago

Figma-Context-MCPmedia

Figma-Context-MCP

Verified · 25 days ago

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

hand-reviewed16k stars72k dl/wkchecked 25 days ago

openshortsmedia

openshorts

Verified · today

Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.

hand-reviewed6.0k starschecked today

ffmpegmedia

FFmpeg

Verified · 4 days ago

Trim, convert, resize, compress, and remix audio and video.

hand-reviewed5.1k starschecked 4 days ago

agent-native-clipsmedia

Agent-Native Clips

Verified · 23 days ago

Screen recording, meeting notes, and voice dictation - all with AI

hand-reviewed4.7k starschecked 23 days ago

claude-real-videomedia

claude-real-video

Verified · today

Let any LLM watch a video locally — and search everything it has ever watched.

hand-reviewed2.2k starschecked today