Pdf2MdCAUTION
PDF to Markdown conversion tool
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@FutureUnreal/mcp-pdf2md) English | 中文
MCP-PDF2MD Service
An MCP-based high-performance PDF to Markdown conversion service powered by MinerU API, supporting batch processing for local files and URL links with structured output.
Key Features
- Format Conversion: Convert PDF files to structured Markdown format.
- Multi-source Support: Process both local PDF files and URL links.
- Intelligent Processing: Automatically select the best processing method.
- Batch Processing: Support multi-file batch conversion for efficient handling of large volumes of PDF files.
- MCP Integration: Seamless integration with LLM clients like Claude Desktop.
- Structure Preservation: Maintain the original document structure, including headings, paragraphs, lists, etc.
- Smart Layout: Output text in human-readable order, suitable for single-column, multi-column, and complex layouts.
- Formula Conversion: Automatically recognize and convert formulas in the document to LaTeX format.
- Table Extraction: Automatically recognize and convert tables in the document to structured format.
- Cleanup Optimization: Remove headers, footers, footnotes, page numbers, etc., to ensure semantic coherence.
- High-Quality Extraction: High-quality extraction of text, images, and layout information from PDF documents.
System Requirements
- Software: Python 3.10+
Quick Start
- Clone the repository and enter the directory:
git clone https://github.com/FutureUnreal/mcp-pdf2md.git cd mcp-pdf2md
- Create a virtual environment and install dependencies:
Linux/macOS:
uv venv source .venv/bin/activate uv pip install -e .
Windows:
uv venv .venv\Scripts\activate uv pip install -e .
- Configure environment variables:
Create a .env file in the project r
9a541037b226OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add pdf2md --env MINERU_API_KEY=${MINERU_API_KEY} -- uvx pdf2md{
"mcpServers": {
"pdf2md": {
"command": "uvx",
"args": [
"pdf2md"
],
"env": {
"MINERU_API_KEY": "${MINERU_API_KEY}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
convert_pdf_file | read | |
convert_pdf_url | read |
Trust audit
CAUTIONgrade B · trust 86/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (2)
.env
.env
Gates applied: no_behavioural_pass.
9a541037b226full audit observations/trust-audit/mcp-server/futureunreal__pdf2md.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 9a541037b226 | CAUTION | B | 86 | first audit |
Questions
What is the Pdf2Md MCP server?
PDF to Markdown conversion tool
What tools does Pdf2Md expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Pdf2Md safe to connect to an agent?
With care. The audit graded it B (86/100) and found 2 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Pdf2Md need?
It reads MINERU_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (9a541037b226), read on 2026-10-08. The repository is watched and re-audited when it changes.