PDF Reader MCP Server
A powerful Model Context Protocol (MCP) server that provides comprehensive PDF processing capabilities, including text extraction, OCR support, and network diagram detection. Designed to work seamlessly with Amazon Q Developer CLI and other MCP-compatible systems.
🚀 Features
- Text Extraction: Extract text content from PDF files with high accuracy
- PDF Analysis: Get comprehensive metadata (pages, document info, encryption status)
- Page-Specific Processing: Extract text from specific pages
- Multi-Language OCR: Support for Thai and English text recognition
- Smart Processing: Automatically chooses between OCR and direct text extraction
- Markdown Conversion: Convert PDF content to clean markdown format
- Document Analysis: Determine if PDFs are scanned images or searchable text
- Network Diagram Detection: Advanced capability to detect and extract network diagrams
- MCP Integration: Seamless integration with Amazon Q Developer CLI
📦 Installation
Using uvx (Recommended)
The easiest way to use this MCP server is with uvx:
# Run directly without installation
uvx pdf-reader-mcp # your mcp client can now connect using both sse and stdio transport
# Or install globally
uvx install pdf-reader-mcp
Using pip
pip install pdf-reader-mcp
From Source
git clone https://github.com/zixma13/pdf-reader-mcp.git
cd pdf-reader-mcp
pip install -e .
📋 Prerequisites
-
Install Tesseract OCR (required for OCR functionality):
# For macOS brew install tesseract brew install tesseract-lang # For language support including Thai # For Ubuntu/Debian # sudo apt-get install tesseract-ocr # sudo apt-get install tesseract-ocr-tha # For Thai language support
-
Install Python dependencies:
pip install -r requirements.txt
-
Ensure you have the virtual environment activated:
source .venv/bin/activate
-
Test the server:
mcp dev main.py
Configuration for Amazon Q Developer CLI
Add the following to your ~/.aws/amazonq/mcp.json file:
- in case you clone the git repository
{
"mcpServers": {
"pdf_reader": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/pdf_reader/pdf_reader",
"run",
"main.py"
]
}
}
}
- in case you use uvx
{
"mcpServers": {
"pdf_reader": {
"command": "uvx",
"timeout": 60000,
"args": [
"pdf-reader-mcp"
]
}
}
}
Usage Examples
Once configured, you can use the PDF reader tools in Amazon Q:
Basic PDF Processing
-
To analyze a PDF and determine if it's a scanned image or searchable text:
pdf_reader___analyze_pdf("/path/to/document.pdf") -
To intelligently extract content from a PDF (automatically choosing between OCR and text extraction):
pdf_reader___smart_extract_pdf("/path/to/document.pdf") -
To intelligently convert a PDF to markdown:
pdf_reader___smart_pdf_to_markdown("/path/to/document.pdf") -
To extract text from a PDF:
pdf_reader___read_pdf("/path/to/document.pdf") -
To get metadata from a PDF:
pdf_reader___get_pdf_metadata("/path/to/document.pdf") -
To extract text from a specific page (0-indexed):
pdf_reader___extract_pdf_page("/path/to/document.pdf", 0) -
To extract text using OCR (supports Thai and English):
pdf_reader___ocr_pdf("/path/to/document.pdf") -
To extract text from a specific page using OCR:
pdf_reader___ocr_pdf_page("/path/to/document.pdf", 0) -
To convert PDF to markdown format:
pdf_reader___pdf_to_markdown("/path/to/document.pdf") -
To convert PDF to markdown format using OCR:
pdf_reader___pdf_to_markdown("/path/to/document.pdf", use_ocr=True)
Metadata
Release files for pdf-reader-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| pdf_reader_mcp-0.1.1.tar.gz | 7.6 kB | Without provenance | Details for pdf_reader_mcp-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| pdf_reader_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for pdf_reader_mcp-0.1.1-py3-none-any.whl |
Total release size: 15.5 kB
Release files / pdf_reader_mcp-0.1.1.tar.gz
| Download URL | pdf_reader_mcp-0.1.1.tar.gz |
|---|---|
| Size | 7.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e9ca1086f458c16c2015f3050d54d1a32f6f34fcbbf89992e6f69d57d6c850e9
|
|
BLAKE2b-256 checksum How to use checksums |
6e5400e5405992ed526971512bcd7babf2e7b268cc71c24b047efdd41a3b2c6e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.12
|
Release files / pdf_reader_mcp-0.1.1-py3-none-any.whl
| Download URL | pdf_reader_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 7.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7d43e6ab4218ac3608e2671c2faa3968671319ef2e3f4d9cdf958a3d782333f2
|
|
BLAKE2b-256 checksum How to use checksums |
a2e3a0fb6e24f1cd21c9c5e5682313def33ba6f507c1d9158901fbc08c043414
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.12
|
Security for pdf-reader-mcp 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.