# mcp-pymupdf [Health: Active]

**Category:** 💻 Developer Tools  
**Repository:** https://github.com/penny4nonsense/mcp-pymupdf  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/mcp-pymupdf

## Description
MCP server for reading PDFs using PyMuPDF. Supports local files and URLs.

## Tools
Capabilities this server exposes over MCP:

- **read_pdf** — Extract text from a PDF file or URL.
- **get_page** — Extract text from a specific page range.
- **get_metadata** — Retrieve PDF metadata without reading full text.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "mcp-pymupdf": {
    "command": "uvx",
    "args": ["mcp-pymupdf"]
  }
}
```

## Documentation & README

# mcp-pymupdf

<!-- mcp-name: io.github.penny4nonsense/mcp-pymupdf -->

An MCP server for reading PDFs using PyMuPDF. Supports local files and URLs.

## Installation

```bash
pip install mcp-pymupdf
```

## Tools

### `read_pdf`
Extract text from a PDF file or URL.

```json
{
  "source": "/path/to/file.pdf",
  "max_pages": 50,
  "max_bytes": 200000
}
```

### `get_page`
Extract text from a specific page range.

```json
{
  "source": "https://example.com/paper.pdf",
  "start_page": 3,
  "end_page": 8
}
```

### `get_metadata`
Retrieve PDF metadata without reading full text.

```json
{
  "source": "/path/to/file.pdf"
}
```

## Usage with Claude Desktop

Add to your Claude Desktop config:

```json
{
  "mcpServers": {
    "pdf": {
      "command": "mcp-pymupdf"
    }
  }
}
```

## Notes

- Scanned or image-based PDFs cannot be read without OCR
- Mathematical notation may render as plain text approximations
- URLs are downloaded to a temp file and deleted after reading

## License

MIT