How do I use mineru-docparse-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mineru-docparse-mcp Convert this PDF to Markdown" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

mineru-docparse-mcp

by zhengjie9510

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

mineru-docparse-mcp

MCP Server that converts Word / PDF / PPT / Excel to Markdown, powered by the MinerU DocParse API.

This project is a protocol wrapper — it does not parse documents itself. You need a running MinerU DocParse service, defaulting to http://localhost:8000. See the MinerU repository for deployment instructions.

Installation

pip install mineru-docparse-mcp

Related MCP server: MCP Document Parse Tool

Setup with Claude Code

The output directory is a server-side setting (not a per-request parameter), so MINERU_OUTPUT_DIR must be configured in advance:

{
  "mcpServers": {
    "mineru": {
      "command": "uvx",
      "args": ["mineru-docparse-mcp"],
      "env": {
        "MINERU_API_URL": "http://localhost:8000",
        "MINERU_OUTPUT_DIR": "/Users/yourname/Documents/mineru-output"
      }
    }
  }
}

Once configured, Claude will automatically invoke the tools below. All parsed results are saved to MINERU_OUTPUT_DIR.

Tools

Tool	Description
`mineru_parse_document`	Convert PDF/Word/PPT/Excel to Markdown, saved to disk
`mineru_health_check`	Check MinerU service health

Output format: Results are saved exactly as returned by MinerU. When response_format_zip=true (the default) output is saved as .zip; when false as .json. File name matches the source file — if a file with the same name already exists, a timestamp is appended to avoid overwriting.

API Parameters

mineru_parse_document mirrors the MinerU /file_parse endpoint:

Parameter	Type	Default	Description
`file_path`	string	required	Local document path (absolute or relative)
`backend`	enum	`hybrid-engine`	Parsing backend, see "backend options" below
`lang_list`	string[]	`["ch"]`	OCR language list, only for `pipeline` backend
`effort`	`medium` \| `high`	`medium`	`hybrid` backends only. `medium`: faster, no chart analysis; `high`: higher accuracy with chart analysis, slower
`parse_method`	`auto` \| `txt` \| `ocr`	`auto`	PDF parsing method for `pipeline`/`hybrid`: auto-detect / text extraction / OCR
`formula_enable`	bool	`true`	Enable formula parsing (LaTeX)
`table_enable`	bool	`true`	Enable table parsing
`image_analysis`	bool	`true`	Enable image/chart analysis (VLM/hybrid backends only)
`server_url`	string \| null	`null`	OpenAI-compatible server URL, required for `*-http-client` backends
`return_md`	bool	`true`	Include Markdown content in response
`return_middle_json`	bool	`false`	Include intermediate JSON in response
`return_model_output`	bool	`false`	Include raw model output JSON in response
`return_content_list`	bool	`false`	Include content list JSON in response
`return_images`	bool	`false`	Include extracted images in response
`response_format_zip`	bool	`true` (this project's default; API default is `false`)	Return results as ZIP (false returns JSON)
`return_original_file`	bool	`false`	Include processed original file in ZIP (`response_format_zip=true` only)
`client_side_output_generation`	bool	`false`	Defer final Markdown/content-list generation to the client
`start_page_id`	int	`0`	Starting page (0-indexed)
`end_page_id`	int	`99999`	Ending page (0-indexed)

Backend Options

Value	Description
`pipeline`	General-purpose, multilingual, no hallucination
`vlm-engine`	Local compute, high accuracy, Chinese/English only
`vlm-http-client`	Remote compute (OpenAI-compatible), high accuracy, Chinese/English only
`hybrid-engine` (default)	Local compute, hybrid parsing, multilingual, tune with `effort`
`hybrid-http-client`	Primarily remote compute + light local, hybrid parsing, multilingual

Language Options (`lang_list`)

ch (Chinese/English/Japanese/Traditional/Latin), ch_server, korean, ta (Tamil), te (Telugu), ka (Kannada), th (Thai), el (Greek), arabic, east_slavic, cyrillic, devanagari. Only applies to the pipeline backend; ignored by others.

Server Configuration (Environment Variables)

These are server startup settings — configure them in the env field of your MCP config, not as per-request parameters.

Variable	Default	Description
`MINERU_API_URL`	`http://localhost:8000`	MinerU service URL
`MINERU_OUTPUT_DIR`	none (required)	Directory for parsed results (absolute or relative paths)
`MINERU_API_TIMEOUT`	`600`	Request timeout in seconds — increase for large files
`MCP_TRANSPORT`	`stdio`	Transport mode: `stdio` (local subprocess) or `streamable-http` (remote)
`MCP_HOST`	`127.0.0.1`	Listen address (HTTP mode only); set to `0.0.0.0` to expose externally
`MCP_PORT`	`8001`	Listen port (HTTP mode only)

Remote Deployment (Optional)

To run the MCP server on a dedicated machine accessible by multiple clients, use HTTP mode:

MCP_TRANSPORT=streamable-http MCP_PORT=8001 MINERU_OUTPUT_DIR=/data/mineru-output uvx mineru-docparse-mcp

Clients connect via URL:

{
  "mcpServers": {
    "mineru": {
      "type": "streamableHttp",
      "url": "http://<server-address>:8001/mcp"
    }
  }
}

Omitting MCP_TRANSPORT defaults to local stdio mode (the "Setup with Claude Code" flow above), which is sufficient for personal use.

FAQ

"MINERU_OUTPUT_DIR environment variable not configured" — This is a required server setting, not an API parameter. Set it in the env field of your MCP config and restart the MCP connection.

"Cannot connect to MinerU service" — Verify MINERU_API_URL is reachable: curl $MINERU_API_URL/health. In stdio mode, environment variables must be set in the MCP config env field; shell export won't work.

Large files timeout — Increase MINERU_API_TIMEOUT or narrow the start_page_id/end_page_id range to parse in batches.

Want JSON instead of ZIP — Set response_format_zip to false; results will be saved as .json instead of .zip.

License

MIT

Available Tools

2 tools

mineru_health_checkA

检查 MinerU DocParse API 服务是否正常运行。

Inputs: no named parameters. Returns: object

mineru_parse_documentC

将 PDF · DOCX · PPTX · XLSX · 图片 · 网页转为结构化 Markdown / JSON

上传文件到 MinerU DocParse API 进行内容提取

Inputs: params (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

A3.5/5.0

Scored 2026-07-11 06:50 across 2 tools

Disambiguation5/5

The two tools serve completely distinct purposes: one checks API health, the other parses documents. There is no overlap or ambiguity.

Naming Consistency5/5

Both tools follow a consistent 'mineru_verb_noun' pattern using snake_case, which is clear and predictable.

Tool Count3/5

Only two tools exist, which is borderline low for a typical server. However, for a focused document parsing service with a health check, it may be acceptable.

Completeness4/5

The set covers the essential operations for the server's purpose: health check and document parsing. Minor gaps like format listing or status checking are absent but workable.

Maintenance

ActivityInactive

ResponsivenessOutdated data

Resources

Related MCP Connectors

stagenth · 文档解析A
com.stagenth
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
RAG Systems File Systems
2
https://stagenth.com/mcp/doc-parse/
flatmarkA
dev.flatmark
Document to Markdown MCP server: PDF, Word, PowerPoint, Excel and HTML, with OCR for large files.
Documentation Access Image & Video Processing Workplace & Productivity
31
https://api.flatmark.dev/mcp/
LlmFilesA
com.llmfiles
Convert PDF, DOCX, XLSX and 25 other formats to clean Markdown for LLMs and RAG. No key or account.
RAG Systems Data Platforms Documentation Access
31
https://llmfiles.com/mcp
MdkitA
online.mdkit
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Developer Tools RAG Systems Data Platforms
1
https://api.mdkit.online/mcp/

Related MCP Servers

Mineru MCP Server
Documentation Access Developer Tools Research & Data
demomagic
A
license
Not graded
quality
D
maintenance
Enables document parsing through the Mineru API with support for multiple formats (PDF, DOC, DOCX, PPT, images), OCR, formula recognition, and table extraction in multiple languages.
Updated a year ago (2025-07-09 16:24 UTC)
1
ISC
MCP Document Parse Tool
Developer Tools File Systems Documentation Access
tianfn
A
license
A
quality
D
maintenance
Enables parsing and extraction of content from various document formats (PDF, Word, Excel, PowerPoint) into Markdown format using the Niutrans document API.
Updated a year ago (2025-12-17 08:45 UTC)
1
5
MIT
MCP Document Parse
Documentation Access File Systems Research & Data
NiuTrans
A
license
A
quality
D
maintenance
Parses various document formats (PDF, Word, Excel, PowerPoint) into Markdown content using NiuTrans API, enabling extraction and reading of document text through natural language interactions.
Updated a year ago (2025-12-19 05:37 UTC)
1
9
MIT
MinerU MCP Server
Documentation Access Multimedia Processing App Automation
Tongzhao9417
A
license
A
quality
D
maintenance
Exposes the MinerU document-to-markdown API as MCP tools for converting PDF, Word, PPT, and images into Markdown. It supports both local and remote file processing with integrated OCR capabilities for multiple languages.
Updated 8 months ago (2026-03-19 09:20 UTC)
2
14 PyPI
10
MIT

mineru-docparse-mcp

Installation

Setup with Claude Code

Tools

API Parameters

Backend Options

Language Options (lang_list)

Server Configuration (Environment Variables)

Remote Deployment (Optional)

FAQ

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Mineru MCP Server

MCP Document Parse Tool

MCP Document Parse

MinerU MCP Server

Language Options (`lang_list`)