lizeur 0.1.0

Lizeur is a MCP server to be able to get content from PDFs.

Lizeur - PDF Content Extraction MCP Server

Lizeur is a Model Context Protocol (MCP) server that enables AI assistants to extract and read content from PDF documents using Mistral AI's OCR capabilities. It provides a simple interface for converting PDF files to markdown text that can be easily consumed by AI models.

Features

• PDF OCR Processing: Uses Mistral AI's latest OCR model to extract text from PDF documents
• Intelligent Caching: Automatically caches processed documents to avoid re-processing
• Markdown Output: Returns clean markdown text for easy integration with AI workflows
• FastMCP Integration: Built with FastMCP for optimal performance and ease of use

Prerequisites

• Python 3.10
• UV package manager
• Mistral AI API key

Installation

1. Clone the Repository

git clone <repository-url>
cd lizeur

2. Create and Activate Virtual Environment

# Create a virtual environment
uv venv --python 3.10

# Activate the virtual environment
# On macOS/Linux:
source .venv/bin/activate

# On Windows:
# .venv\Scripts\activate

3. Install Dependencies and Build

# Install dependencies
uv sync

# Build the package
uv build

4. Install System-Wide

# Install the package system-wide
uv pip install --system .

This will install the lizeur command globally on your system.

MCP Configuration

Add the following configuration to your mcp.json file:

{
  "mcpServers": {
    "lizeur": {
      "command": "lizeur",
      "env": {
        "MISTRAL_API_KEY": "your-mistral-api-key-here",
        "CACHE_PATH": "your cache path",
      }
    }
  }
}

Usage

Once configured, the MCP server provides a read_pdf tool that can be used by AI assistants:

• Function: read_pdf
• Parameter: absolute_path (string) - The absolute path to the PDF file
• Returns: Markdown text extracted from the first page of the PDF

Example Usage in AI Assistant

The AI assistant can now use the tool like this:

What the OP code looks like for this specific controller, here is the doc /path/to/document.pdf

The MCP server will:

1. Check if the document is already cached
2. If not cached, upload the PDF to Mistral AI for OCR processing This will use your MISTRAL API key and cost money
3. Extract the text and convert it to markdown
4. Cache the result for future use
5. Return the markdown content

Development

Local Development Setup

# Install in development mode
uv pip install -e .

# Run the server directly
python main.py

Project Structure

• main.py - Main server implementation with FastMCP integration
• pyproject.toml - Project configuration and dependencies
• uv.lock - Locked dependency versions

Dependencies

• mcp[cli]>=1.12.4 - Model Context Protocol implementation
• mistralai>=0.0.10 - Mistral AI Python client

License

This project is marked as private and should not be uploaded to public package repositories.

Support

For issues and questions, please refer to the project repository or contact the maintainers.