MCP Mistral Ocr

🚀 MCP Mistral OCR

An MCP server that uses Mistral AI's OCR API to provide optical character recognition capabilities. This server supports processing local files and URLs, suitable for images and PDFs.

🚀 Quick Start

MCP Mistral OCR is an MCP server that leverages Mistral AI's OCR API to offer optical character recognition functionality. It can handle both local files and URLs, supporting images and PDFs.

✨ Features

• Process local files (images and PDFs) using Mistral's OCR.
• Handle URL files with explicit file type specification.
• Support multiple file formats (JPG, PNG, PDF, etc.).
• Save results as timestamped JSON files.
• Containerized with Docker.
• Managed by UV package manager.

🔧 Environment Variables

📦 Installation

Install via Smithery

To automatically install Mistral OCR for Claude Desktop via Smithery:

npx -y @smithery/cli install @everaldo/mcp/mistral-crosswalk --client claude

Using Docker

1. Build the Docker image:

docker build -t mcp-mistral-ocr .

2. Run the container:

docker run -e MISTRAL_API_KEY=your_api_key -e OCR_DIR=/data/ocr -v /path/to/local/files:/data/ocr mcp-mistral-ocr

Local Development

1. Install the UV package management tool:

pip install uv

2. Create and activate a virtual environment:

uv venv
source .venv/bin/activate  # On Unix systems
# Or on Windows systems
.venv\Scripts\activate

3. Install dependencies:

uv pip install .

📚 Configuration for Claude Desktop

Add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "mistral-ocr": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MISTRAL_API_KEY",
        "-e",
        "OCR_DIR",
        "-v",
        "C:/path/to/your/files:/data/ocr",
        "mcp-mistral-ocr:latest"
      ],
      "env": {
        "MISTRAL_API_KEY": "<YOUR_MISTRAL_API_KEY>",
        "OCR_DIR": "C:/path/to/your/files"
      }
    }
  }
}

💻 Usage Examples

Available Tools

1. process_local_file

Process files in the OCR_DIR directory.

{
    "name": "process_local_file",
    "arguments": {
        "filename": "document.pdf"
    }
}

2. process_url_file

Process files from URLs. An explicit file type needs to be specified.

{
    "name": "process_url_file", 
    "arguments": {
        "url": "https://example.com/document",
        "file_type": "image" // or "pdf"
    }
}

📈 Output

OCR results are saved in the output folder within the OCR_DIR directory. Each result file is named in the following format:

• For local files: {original_filename}_{timestamp}.json
• For URLs: {url_filename}_{timestamp}.json or url_document_{timestamp}.json (if no filename is found in the URL). The timestamp format is YYYYMMDD_HHMMSS.

📄 Supported File Types

• Images: JPG, JPEG, PNG, GIF, WebP
• PDF

⚠️ Important Note

Please ensure the security of your API key and avoid exposing it in plain text environments.