mineru-tianshu
天枢 - 企业级 AI 一站式数据预处理平台 | PDF/Office转Markdown | 支持MCP协议AI助手集成 | Vue3+FastAPI全栈方案 | 文档解析 | 多模态信息提取
No outside reports on file
Treat documents as untrusted input: only process files from sources you trust, because malicious PDFs or Office files could leak data to your AI or try to execute code.
Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesReads local filesNOTED
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (magicyuan876/mineru-tianshu)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/magicyuan876/mineru-tianshu ↗
About Mineru Tianshu
This tool converts PDFs and Office documents (like Word files) into Markdown format. It can extract text, images, tables, and other content from documents and works with AI assistants using the MCP protocol (a standard for connecting tools to AI).
Who it’s for
Teams and companies that need to process many documents automatically and want to feed document content to AI assistants. It's built with Vue3 (a web framework) and FastAPI (a backend framework).
Alternatives
- Apache Tika: Open-source document parsing tool that converts many file types to text.
- Docling (IBM): Document intelligence tool for converting PDFs and documents to structured formats.
- LlamaParse: Paid service for parsing and extracting data from documents via API.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/magicyuan876/mineru-tianshu (opens external site) for installation instructions, as setup may require Python dependencies and configuration steps specific to this tool.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 849
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- File access: The tool reads files from your system and can process any PDF or Office document you point it at, so malicious files could try to exploit the parsing engine.
- Markdown injection: A crafted PDF or Office file might contain hidden commands or code disguised as text that looks normal but could confuse an AI assistant.
- Data leakage: Extracted document content is converted to Markdown and sent to connected AI systems; sensitive information in documents (passwords, personal data, emails) could be exposed.
- Code execution: If the tool uses unsafe parsing libraries, a specially crafted file might attempt to run code on your computer.
- Man-in-the-middle risk: If the MCP connection isn't encrypted, data traveling between this tool and your AI assistant could be intercepted.
How to lower the risk
Least-privilege permissions
- Run the tool on a user account with limited file system access, not as admin.
- Only grant it access to document folders it truly needs.
Network isolation
- Keep the tool on a private network or behind a firewall if possible.
- Don't expose the web interface to the internet.
Monitoring
- Log which documents are processed and when.
- Watch for unusual CPU or memory spikes that might indicate an attack.
Red flags to watch for
- Errors or crashes when processing certain files could mean a malicious document.
- Unexpected network connections from the tool's process.
Questions
How do I install Mineru Tianshu?
Mineru Tianshu does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/magicyuan876/mineru-tianshu.
Are there security reports about Mineru Tianshu?
No reports found for this package in our research (last checked 2026-10-29). Mineru Tianshu currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include file access, markdown injection, data leakage.
Is Mineru Tianshu actively maintained?
Mineru Tianshu has 849 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/magicyuan876/mineru-tianshu before pinning it in production.
What are alternatives to Mineru Tianshu?
Notable alternatives to Mineru Tianshu include Apache Tika (Open-source document parsing tool that converts many file types to text), Docling, LlamaParse (Paid service for parsing and extracting data from documents via API). You can also compare Mineru Tianshu side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Mineru Tianshu? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/magicyuan876-mineru-tianshu)HTML embed:
<a href="https://agentarmorhq.com/skills/magicyuan876-mineru-tianshu"><img src="https://agentarmorhq.com/api/badge/magicyuan876-mineru-tianshu" alt="AgentArmorHQ Risk Grade for Mineru Tianshu" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "magicyuan876-mineru-tianshu"Share with your security lead
Need sign-off to use mineru-tianshu? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: mineru-tianshu
- **Listing URL:** https://agentarmorhq.com/skills/magicyuan876-mineru-tianshu
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 849 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** Reads local files
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (magicyuan876/mineru-tianshu)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/magicyuan876/mineru-tianshu
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- magicyuan876
- Source code
- github.com/magicyuan876/mineru-tianshu
- Est. context load
- ~550 tokens / turn (~3 tool schemas, 0.27% of 200k context)
- Popularity
- 849 GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-24
Community
Discussions for Mineru Tianshu
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude