How do I use mineru-docparse-mcp?

1. Click on "Install 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 Related Servers Score Discussions

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。

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description is minimal—it does not disclose behavioral traits such as side effects, authentication needs, or rate limits, which is a gap for a tool with no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words, achieving maximum conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple health-check tool with no parameters and an output schema present, the description adequately states its purpose, though it could hint at usage context (e.g., check before parsing).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters and schema coverage is 100%, so the baseline is 4; the description adds no param information, but none is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks the health of the MinerU DocParse API service, using a specific verb ('check') and resource, and it is distinct from the sibling tool that parses documents.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for health checking but does not explicitly state when to use versus alternatives (e.g., before parsing), and provides no exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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

ParametersJSON Schema

Name	Required	Description	Default
`params`	Yes	mineru_parse_document 的输入参数，对应官方 POST /file_parse 接口。字段及默认值与官方 OpenAPI schema 一致，仅 response_format_zip 默认改为 True。

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It mentions uploading to an API but does not disclose side effects, authentication requirements, rate limits, or non-destructive nature. Transparency is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise (two sentences), front-loading the core function and supported formats. Every word adds value, though it could be slightly more structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple backends, many parameters, nested input), the description is too brief. It lacks a high-level overview of backends, output behavior, and potential caveats, leaving the agent to infer from the schema alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline 3 is appropriate. The tool description does not add detail beyond the schema, but the nested params description within the input schema provides comprehensive parameter meanings.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool converts PDF, DOCX, PPTX, XLSX, images, and web pages to structured Markdown/JSON, and uploads to the MinerU DocParse API for extraction. It differentiates from the sibling health check tool by its specific parsing function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor are there any prerequisites or exclusions. The description only defines the action without contextual usage advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

2 tool updatesv1.0.0Jul 11, 2026
- First observedmineru_health_check
- First observedmineru_parse_document

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

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

ActivitySlowing

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

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
42
Mdkit A
online.mdkit
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Developer Tools RAG Systems Data Platforms
31
file2markdown A
ai.file2markdown
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Browser Automation Documentation Access Web Scraping
41
agentmd A
io.github.djrobson5
Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved
Documentation Access Web Scraping
21

Related MCP Servers

Mineru MCP Server
Documentation Access Developer Tools Research & Data
demomagic
F
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
-
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 9 months 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 9 months 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 6 months ago (2026-03-19 09:20 UTC)
2
10
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zhengjie9510/mineru-docparse-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

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

Output Schema

TDQS

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Mineru MCP Server

MCP Document Parse Tool

MCP Document Parse

MinerU MCP Server

Latest Blog Posts

MCP directory API

Language Options (`lang_list`)