MinerU
Wraps MinerU's document parsing API with six tools for extracting text, tables, and formulas from PDFs, Office docs, and images. You get mineru_parse for single URLs, mineru_upload_batch for local files, and mineru_batch for up to 200 documents at once. Status and download tools handle async workflows and save results as markdown with preserved filenames. Supports two models: pipeline for speed on simple docs, VLM for 90%+ accuracy on complex layouts. Includes OCR across 109 languages and page range selection. Requires a MinerU API key. Reach for this when you need production document extraction without running models locally, especially for batch processing scanned PDFs or converting documentation archives to markdown.
- GitHub stars
- 10
- tools
- 14
- transport
- STDIO
- last updated
- Nov 7, 2026
Tools
14 toolsPublic tool metadata for what this MCP can expose to an agent.
mineru_parseParse a document URL
Parse a document URL
No parameter schema in public metadata yet.
mineru_statusCheck task progress, get download URL
Check task progress, get download URL
No parameter schema in public metadata yet.
mineru_batchParse multiple URLs
Parse multiple URLs
No parameter schema in public metadata yet.
mineru_batch_statusGet batch results with pagination
Get batch results with pagination
No parameter schema in public metadata yet.
mineru_upload_batchUpload local files for batch parsing
Upload local files for batch parsing
No parameter schema in public metadata yet.
mineru_download_resultsRetain complete archives, inventory all members, and create named compatibility copies
Retain complete archives, inventory all members, and create named compatibility copies
No parameter schema in public metadata yet.
mineru_parse_longSubmit a long document as a batch of page-range slices
Submit a long document as a batch of page-range slices
No parameter schema in public metadata yet.
mineru_merge_slicesJoin available Markdown and retain immutable slice archives with explicit unknown page provenance
Join available Markdown and retain immutable slice archives with explicit unknown page provenance
No parameter schema in public metadata yet.
mineru_capabilitiesRead locally known capabilities; explicit refresh performs discovery
Read locally known capabilities; explicit refresh performs discovery
No parameter schema in public metadata yet.
mineru_submitSubmit with a durable local journal and duplicate-request protection
Submit with a durable local journal and duplicate-request protection
No parameter schema in public metadata yet.
mineru_operation_statusRead a recorded operation; explicit refresh checks remote status
Read a recorded operation; explicit refresh checks remote status
No parameter schema in public metadata yet.
mineru_resumeContinue safe recorded checkpoints
Continue safe recorded checkpoints
No parameter schema in public metadata yet.
mineru_cancelStop local processing; remote cancellation is unsupported
Stop local processing; remote cancellation is unsupported
No parameter schema in public metadata yet.
mineru_bundleValidate and return an operation's retained bundle
Validate and return an operation's retained bundle
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
mineru-mcp
MCP server and mineru-cloud CLI for the MinerU document
parsing API, with complete artifact retention, durable operations, and portable
PDF bundles.
Version 2.0.0 is the first npm release with durable operations and portable
bundles. It requires Node.js 20 or newer; stay on mineru-mcp@1 for Node.js 18.
Features
- VLM model — Document parsing with a vision-language model
- Pipeline model — Document parsing with the pipeline model
- Local file upload — Upload files from disk for batch parsing
- Batch processing — Submit multiple documents in one request
- Download & rename — Extract markdown with original filenames
- Page ranges — Extract specific pages only
- Long documents —
mineru_parse_longsubmits page-range slices andmineru_merge_slicesstitches - CLI twin —
mineru-cloudcalls the same tools from a shell - Language and OCR options — Select a language and enable OCR for the pipeline model
Tools
Details
- Repository
- github.com/linxule/mineru-mcp
- Categories
- Documents & Knowledge, Productivity & Office
- Package
mineru-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from linxule
Related Documents & Knowledge MCP servers
View all
OpenArxopenarx-ai/openarx-coreOpen scientific and engineering knowledge for AI agents: search, evidence, document publishing.0stars
Rendex: Rendering API for Images, PDFs & Content Extractioncopperline-labs/rendex-mcpRender HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.6stars
Jira Mcpraalarcon9705/jira-mcpJira & Confluence MCP: 24 tools for issues, sprints, comments, transitions & wiki. Run via npx.4stars
kObsidianbezata/kobsidianFilesystem-first MCP for Obsidian — an LLM-maintained wiki inspired by Karpathy's LLM Wiki.3stars
SnapRenderuser0856/snaprender-integrationsGive AI agents eyes: screenshot any URL as PNG, JPEG, WebP or PDF, or read it as markdown.0stars
markitdown-rsmajiayu000/markitdown-rsConvert PDF, Word, Excel, PowerPoint, HTML, EPUB and URLs to Markdown; markitdown-mcp in Rust3stars