io.github.opendatalab/mineru-open-mcpmedia

MinerU Open MCP

Verified · 22 days ago

Parse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.

Install

claude mcp add mineru-open-mcp -- uvx mineru-open-mcp

Requires: MINERU_API_TOKEN, OUTPUT_DIR

Our take

A document-parsing MCP server that converts PDFs, office files, images, and HTML into Markdown using the MinerU API. It is aimed at ingestion pipelines, RAG setups, and automation workflows that need normalized text from mixed document formats. The scope is practical and clear, but reliance on an external API means quality and cost will track the underlying service.

reviewed by hand · 2026-07-10

Something wrong or dead here? Report it

Verification record

last verified: 22 days ago
github stars: 168
last commit: 3 mo ago
archived: no
license: Apache-2.0
in registry since: 2026-04-13

github.com/opendatalab/MinerU-Ecosystem

More in media

funasr-mcpmedia

FunASR

Verified · 6 days ago

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

hand-reviewed20k starschecked 6 days ago

Figma-Context-MCPmedia

Figma-Context-MCP

Verified · 8 days ago

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

hand-reviewed16k stars95k dl/wkchecked 8 days ago

openshortsmedia

openshorts

Verified · 16 days ago

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

hand-reviewed2.9k starschecked 16 days ago

claude-real-videomedia

claude-real-video

Verified · 16 days ago

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

hand-reviewed1.9k starschecked 16 days ago

Figma MCP Server

Verified · 11 days ago

The Figma MCP server brings Figma design context directly into your AI workflow.

hand-reviewed1.9k starschecked 11 days ago

voicemodemedia

voicemode

Verified · 9 days ago

Natural voice conversations for AI assistants - STT/TTS via MCP

hand-reviewed1.3k starschecked 9 days ago